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

    Neuronpedia

    INDEX
    Explanations

    code and technical docs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dese
    -0.07
    (Pos
    -0.07
     Et
    -0.07
     DEN
    -0.07
    uluğ
    -0.06
     Cultural
    -0.06
    .ag
    -0.06
     connected
    -0.06
     Braz
    -0.06
     unh
    -0.06
    POSITIVE LOGITS
    _LOWER
    0.07
    ermo
    0.06
     відбувається
    0.06
    clamp
    0.06
    ERSION
    0.06
    ฒ
    0.06
    onium
    0.06
     помощи
    0.06
    Exit
    0.06
    ULLET
    0.06
    Act Density 0.000%

    No Known Activations