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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seguint
    -0.07
     champions
    -0.07
     Wayne
    -0.06
    mium
    -0.06
    iddles
    -0.06
    iš
    -0.06
    Authors
    -0.06
     Missile
    -0.06
    executable
    -0.06
     manuscripts
    -0.06
    POSITIVE LOGITS
    .fastjson
    0.09
    uellen
    0.07
     tranqu
    0.06
    �
    0.06
    itori
    0.06
     satisf
    0.06
    叔
    0.06
    .getComponent
    0.06
     ties
    0.06
    ********************************************************
    0.06
    Act Density 0.014%

    No Known Activations