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

    Neuronpedia

    INDEX
    Explanations

    filepaths and code artifacts, possibly related to compilation or tracing

    oai_token-act-pair · gemini-2.0-flash

    ctx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feroit
    -1.72
     تضيفلها
    -1.65
     auroit
    -1.60
    complexContent
    -1.59
     pouvoit
    -1.59
    ьаж
    -1.59
     Roskov
    -1.55
     étoit
    -1.53
    IntoConstraints
    -1.52
    berdayakan
    -1.51
    POSITIVE LOGITS
     
    1.13
    .
    1.01
    ↵↵
    1.00
    ↵
    0.97
    The
    0.91
    1
    0.91
    2
    0.89
    _
    0.88
    -
    0.85
    *
    0.82
    Act Density 1.492%

    No Known Activations