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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iva
    -0.06
     aan
    -0.06
     condom
    -0.06
    еними
    -0.06
     زي
    -0.06
    _cons
    -0.06
     вина
    -0.06
    lenmesi
    -0.06
     presentations
    -0.06
    Destroy
    -0.06
    POSITIVE LOGITS
    .Render
    0.07
    .t
    0.07
    -unit
    0.07
     行
    0.06
    -T
    0.06
    .fb
    0.06
     �
    0.06
    友
    0.06
    .angle
    0.06
    selectors
    0.06
    Act Density 0.000%

    No Known Activations