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

    Neuronpedia

    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evidence
    -0.74
    evidence
    -0.60
     Evidence
    -0.54
     preuves
    -0.52
     EVIDENCE
    -0.51
    Evidence
    -0.47
    ghar
    -0.47
     travail
    -0.45
    ilir
    -0.43
    -
    -0.43
    POSITIVE LOGITS
    <bos>
    1.08
     calendriers
    0.91
    GEBURTSDATUM
    0.83
    OGND
    0.75
    EndInit
    0.73
    StructEnd
    0.73
    sizeCache
    0.71
     disponibilités
    0.71
    DockStyle
    0.70
     CURIAM
    0.69
    Act Density 0.066%

    No Known Activations