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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    につ
    -0.07
    唇
    -0.07
    acro
    -0.06
    /notification
    -0.06
     celebration
    -0.06
     Kn
    -0.06
     دی
    -0.06
    det
    -0.06
    _rank
    -0.06
    .components
    -0.06
    POSITIVE LOGITS
     humanity
    0.08
     priesthood
    0.07
     мере
    0.07
    locator
    0.07
     skyline
    0.07
    TypeError
    0.06
     اندازه
    0.06
     Helena
    0.06
     zwe
    0.06
     Lara
    0.06
    Act Density 0.207%

    No Known Activations