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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _some
    -0.06
     Finger
    -0.06
     unbelievable
    -0.06
     pornofil
    -0.06
    .fi
    -0.06
    ง
    -0.06
    yards
    -0.06
    -how
    -0.06
     sor
    -0.06
     lot
    -0.06
    POSITIVE LOGITS
    combined
    0.07
     dominant
    0.07
    ToString
    0.07
     HI
    0.06
    ocusing
    0.06
     inevitably
    0.06
    alarında
    0.06
     Townsend
    0.06
     Statement
    0.06
     �
    0.06
    Act Density 0.016%

    No Known Activations