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

    Neuronpedia

    INDEX
    Explanations

    post

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getitem
    -0.07
    _detection
    -0.06
    BJECT
    -0.06
     dateTime
    -0.06
     vad
    -0.06
     )↵
    -0.06
    (dummy
    -0.06
    achat
    -0.06
     logical
    -0.06
     surgeons
    -0.06
    POSITIVE LOGITS
    nm
    0.07
    ні
    0.07
    resent
    0.07
     Highlight
    0.07
    NT
    0.06
     스타
    0.06
    geme
    0.06
    .ns
    0.06
    nie
    0.06
    лич
    0.06
    Act Density 0.001%

    No Known Activations