Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Conditional statements

    np_max-act · gemini-2.0-flash

    phrases starting with "In" at the beginning of a document.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @chuloivawork

    This neuron activates on the leading phrase “In the” at the start of a sentence.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     justification
    -0.06
    incinn
    -0.06
     ignorant
    -0.06
    Speed
    -0.06
    brook
    -0.05
     POW
    -0.05
     legalization
    -0.05
    フォ
    -0.05
     literature
    -0.05
    WG
    -0.05
    POSITIVE LOGITS
     baktı
    0.07
     incluso
    0.07
    анії
    0.07
    bra
    0.07
     olmadan
    0.07
     cigaret
    0.06
     viability
    0.06
    eson
    0.06
    üncü
    0.06
    .des
    0.06
    Act Density 0.034%

    No Known Activations