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

    Neuronpedia

    INDEX
    Explanations

    avoid change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bad
    -0.08
    Band
    -0.08
    <Map
    -0.07
    Quant
    -0.07
    itable
    -0.06
     mocker
    -0.06
    vek
    -0.06
     sack
    -0.06
    .dec
    -0.06
     모습
    -0.06
    POSITIVE LOGITS
    mdp
    0.07
    ained
    0.06
     جان
    0.06
     representations
    0.06
    .userAgent
    0.06
    BracketAccess
    0.06
     StartTime
    0.06
     yytype
    0.06
     arsch
    0.06
    umed
    0.06
    Act Density 0.010%

    No Known Activations