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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	option
    -0.07
    uja
    -0.07
     επ
    -0.06
     грав
    -0.06
    uv
    -0.06
    .cond
    -0.06
    pls
    -0.06
    slider
    -0.06
    _quick
    -0.06
     LeBron
    -0.06
    POSITIVE LOGITS
     outsiders
    0.07
    اعات
    0.07
     Chinese
    0.06
     Tenn
    0.06
    ouncill
    0.06
    谋
    0.06
    Listening
    0.06
    ereal
    0.06
     Queensland
    0.06
     eerie
    0.06
    Act Density 0.009%

    No Known Activations