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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Duch
    -0.07
     �
    -0.06
     Jaw
    -0.06
     بك
    -0.06
    _Y
    -0.06
     angel
    -0.06
    .LogWarning
    -0.06
    indeki
    -0.06
    oord
    -0.06
    \Route
    -0.06
    POSITIVE LOGITS
     rooting
    0.07
    )NULL
    0.06
    pdb
    0.06
    ovenant
    0.06
     caramel
    0.06
    Score
    0.06
     часов
    0.06
    /global
    0.06
    ，此
    0.06
     misrepresented
    0.06
    Act Density 0.027%

    No Known Activations