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

    Neuronpedia

    INDEX
    Explanations

    chess notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surrender
    -0.07
    bě
    -0.07
     west
    -0.06
     journey
    -0.06
    .ID
    -0.06
     asks
    -0.06
    .sms
    -0.06
     EditText
    -0.06
    .proc
    -0.06
    .tags
    -0.06
    POSITIVE LOGITS
     ------------------------------------------------------------
    0.07
    mighty
    0.07
    Healthy
    0.06
    _predict
    0.06
    ें।
    0.06
    protein
    0.06
    瓶
    0.06
     extravagant
    0.06
     vfs
    0.06
    /*------------------------------------------------
    0.06
    Act Density 0.002%

    No Known Activations