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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     admits
    -0.07
     mol
    -0.07
    tingham
    -0.06
     Transmit
    -0.06
     exponential
    -0.06
    .Information
    -0.06
     グ
    -0.06
     debilitating
    -0.06
     содерж
    -0.06
     WITH
    -0.06
    POSITIVE LOGITS
    1
    0.09
    0
    0.08
    5
    0.08
    2
    0.08
    6
    0.07
    ايا
    0.07
    (...
    0.07
     youtube
    0.07
    /*!
    0.07
    4
    0.07
    Act Density 0.099%

    No Known Activations