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

    Neuronpedia

    INDEX
    Explanations

    public (related to code)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __':
    -0.64
    存于互联网档案馆
    -0.60
    __":
    -0.56
    getValueAt
    -0.55
    ajuato
    -0.53
     MainAxisSize
    -0.53
    __":
    -0.52
    zuführen
    -0.50
    lapsingToolbar
    -0.50
    underland
    -0.49
    POSITIVE LOGITS
     from
    0.54
    AntiForgeryToken
    0.51
    vesse
    0.49
    είο
    0.49
     hydrated
    0.48
     Wheeler
    0.48
     Weyl
    0.46
    клопе
    0.46
    Vezi
    0.46
    Unmount
    0.46
    Act Density 0.005%

    No Known Activations