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

    Neuronpedia

    INDEX
    Explanations

    Anat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FF
    -0.07
     bullied
    -0.06
     �
    -0.06
    quential
    -0.06
    _pool
    -0.06
     youngest
    -0.06
     非
    -0.06
     setups
    -0.06
     Bucket
    -0.06
    rieving
    -0.06
    POSITIVE LOGITS
    recogn
    0.07
    ,p
    0.07
    .dump
    0.07
    StepThrough
    0.06
    ån
    0.06
    AxisAlignment
    0.06
     Warner
    0.06
    Fonts
    0.06
     başlamış
    0.06
    SuccessListener
    0.06
    Act Density 0.000%

    No Known Activations