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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    precio
    -0.07
     shootings
    -0.07
    .subscriptions
    -0.06
     hay
    -0.06
     видно
    -0.06
    Uploader
    -0.06
     spokesman
    -0.06
    xp
    -0.06
     guerr
    -0.06
    XH
    -0.06
    POSITIVE LOGITS
     Toyota
    0.07
    Toyota
    0.07
    ",(
    0.07
    \"";↵
    0.07
     Gardens
    0.07
    PACKAGE
    0.07
    _sw
    0.06
    _reply
    0.06
    Canceled
    0.06
     yielding
    0.06
    Act Density 0.004%

    No Known Activations