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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron responds to domain‐specific nouns describing a company’s core operations or commitments (e.g., “production,” “environment,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nasty
    -0.08
     ruku
    -0.07
    ，把
    -0.06
    holding
    -0.06
     Sour
    -0.06
     Tür
    -0.06
    .col
    -0.06
    شب
    -0.06
     peeled
    -0.06
     найкра
    -0.06
    POSITIVE LOGITS
     tunnels
    0.06
     Come
    0.06
    .sam
    0.06
    MERCHANTABILITY
    0.06
    !↵↵↵↵↵↵
    0.06
     Howard
    0.06
     Geneva
    0.06
     prematurely
    0.06
    (土
    0.06
     phenomena
    0.06
    Act Density 0.038%

    No Known Activations