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

    Neuronpedia

    INDEX
    Explanations

    Breaking rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rond
    -0.06
    Ether
    -0.06
    .social
    -0.06
    unes
    -0.06
    “Oh
    -0.06
     Hanna
    -0.06
    ="'
    -0.06
    [val
    -0.06
     Cater
    -0.06
    :'
    -0.06
    POSITIVE LOGITS
    _GREEN
    0.06
    ители
    0.06
     симптомы
    0.06
    FileChooser
    0.06
     работ
    0.06
    شور
    0.06
     इन
    0.06
     VIDEO
    0.06
    避
    0.06
    XXX
    0.06
    Act Density 0.044%

    No Known Activations