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
    'ya
    -0.07
    isting
    -0.07
     会
    -0.07
     ア
    -0.07
    NG
    -0.06
    IST
    -0.06
    ender
    -0.06
     onPress
    -0.06
    vw
    -0.06
    endors
    -0.06
    POSITIVE LOGITS
    -enh
    0.08
     dostal
    0.07
    úp
    0.07
     tamb
    0.06
     Oriental
    0.06
    ]").
    0.06
     Permit
    0.06
    $headers
    0.06
     Cecil
    0.06
    .getChildAt
    0.06
    Act Density 0.125%

    No Known Activations