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

    Neuronpedia

    INDEX
    Explanations

    technical documentation/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reefs
    -1.07
     reef
    -0.81
     Reef
    -0.63
    reef
    -0.63
    󠁢
    -0.50
    fetera
    -0.49
    sumoto
    -0.49
     financières
    -0.49
     bőr
    -0.48
    mistic
    -0.48
    POSITIVE LOGITS
    ResumeLayout
    0.82
    OGND
    0.69
     ModelExpression
    0.65
    ⓧ
    0.64
     kasarigan
    0.62
     Waray
    0.61
    ViewFeatures
    0.61
    Билгалдахарш
    0.59
    classnames
    0.58
    writeField
    0.57
    Act Density 0.027%

    No Known Activations