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

    Neuronpedia

    INDEX
    Explanations

    causal and ellipses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ·
    -0.81
    <bos>
    -0.69
     ActivatedRoute
    -0.66
    lgari
    -0.62
     initComponents
    -0.57
     ·
    -0.56
    ModelSerializer
    -0.55
    higan
    -0.55
    /$',
    -0.55
     onCreateView
    -0.54
    POSITIVE LOGITS
     Económica
    0.54
     juridiques
    0.54
     desejo
    0.53
    rrggbb
    0.50
     opérateur
    0.50
    abestanden
    0.50
     sonho
    0.48
    ształ
    0.46
     fédé
    0.46
     himo
    0.46
    Act Density 0.007%

    No Known Activations