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

    Neuronpedia

    INDEX
    Explanations

    python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ariance
    -0.07
     Vác
    -0.07
     جمهور
    -0.06
    record
    -0.06
    Interop
    -0.06
     Bout
    -0.06
    ™
    -0.06
    -----
    -0.06
     depress
    -0.06
     له
    -0.06
    POSITIVE LOGITS
    (tmp
    0.07
    那些
    0.06
    Resolver
    0.06
     observation
    0.06
    .toObject
    0.06
    [label
    0.06
    Texture
    0.06
    組
    0.06
    _LOOKUP
    0.06
    akespeare
    0.06
    Act Density 0.001%

    No Known Activations