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

    Neuronpedia

    INDEX
    Explanations

    currently

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demise
    -0.07
    Identification
    -0.07
     kidnapping
    -0.07
     snake
    -0.06
     TTL
    -0.06
     Shane
    -0.06
     Ingredients
    -0.06
     lazy
    -0.06
     boz
    -0.06
     Johann
    -0.06
    POSITIVE LOGITS
    encent
    0.07
    ßer
    0.07
     currently
    0.07
    يير
    0.07
     SUR
    0.07
    -null
    0.07
    {(
    0.07
    ından
    0.07
    342
    0.06
    /at
    0.06
    Act Density 0.019%

    No Known Activations