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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -1.02
     Савезне
    -0.93
    SourceChecksum
    -0.84
    "،
    -0.83
    ...",
    -0.83
    ...")
    -0.82
    ...".
    -0.77
     ComVisible
    -0.76
    ^(@)
    -0.75
    )".
    -0.75
    POSITIVE LOGITS
    </em>
    0.63
    .
    0.56
     –
    0.50
    </blockquote>
    0.47
    –
    0.46
    </strong>
    0.44
    .​
    0.43
     é
    0.42
    <em>
    0.42
    é
    0.42
    Act Density 0.045%

    No Known Activations