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

    Neuronpedia

    INDEX
    Explanations

    code, non-english

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TXT
    -0.08
    екти
    -0.08
    ജന
    -0.08
     headlines
    -0.07
    (ok
    -0.07
    সূচ
    -0.07
    േറ്റ
    -0.07
    ोष
    -0.07
    क्ष
    -0.07
    selection
    -0.07
    POSITIVE LOGITS
     Battle
    0.08
     Whenever
    0.08
     Rück
    0.08
    Collateral
    0.08
     balik
    0.08
     Maint
    0.08
     gabe
    0.08
     anual
    0.08
    emento
    0.08
     coughing
    0.08
    Act Density 0.000%

    No Known Activations