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

    Neuronpedia

    INDEX
    Explanations

    Must or not

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric constants in code, particularly decimal and floating-point literals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Worship
    -0.06
     Kumar
    -0.06
    アン
    -0.06
     أد
    -0.06
     milling
    -0.06
     furry
    -0.06
     boxing
    -0.06
     pulver
    -0.06
    lobber
    -0.06
     mentoring
    -0.06
    POSITIVE LOGITS
    ικής
    0.07
     искус
    0.06
    OKIE
    0.06
    adows
    0.06
    cha
    0.06
     gfx
    0.06
    .clf
    0.06
     NOT
    0.06
    EEP
    0.06
     egy
    0.06
    Act Density 0.014%

    No Known Activations