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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric quantity tokens—especially decimal numbers or other measured values (e.g. “2.326171875,” “0.90771484375,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    —even
    -0.07
    -looking
    -0.06
     рос
    -0.06
     Kansas
    -0.06
    .listFiles
    -0.06
    resizing
    -0.06
    ;display
    -0.06
     слу
    -0.06
     Citizenship
    -0.06
     courthouse
    -0.06
    POSITIVE LOGITS
    atas
    0.07
    lette
    0.07
    _damage
    0.07
     G
    0.06
    at
    0.06
     K
    0.06
    .mybatis
    0.06
    ,
    0.06
    ersistence
    0.06
    iplina
    0.06
    Act Density 0.031%

    No Known Activations