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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出版年
    -0.58
    dopodob
    -0.56
    +:+
    -0.55
    ougou
    -0.54
     BrowserModule
    -0.53
    horabuena
    -0.53
     FEW
    -0.53
     procé
    -0.52
    tableFuture
    -0.52
     malheure
    -0.52
    POSITIVE LOGITS
    orses
    0.58
    izes
    0.58
    tifies
    0.56
    pement
    0.54
     really
    0.54
    ifies
    0.50
    DockStyle
    0.49
    pires
    0.49
    ValueStyle
    0.49
    windowFixed
    0.48
    Act Density 0.001%

    No Known Activations