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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     назива
    -0.06
     받
    -0.06
    Digest
    -0.06
     Foods
    -0.06
    ник
    -0.06
    _vis
    -0.06
    其实
    -0.06
     Β
    -0.05
    National
    -0.05
     Gathering
    -0.05
    POSITIVE LOGITS
     LETTER
    0.07
     cams
    0.07
    IGGER
    0.07
     porno
    0.07
     сель
    0.06
    oenix
    0.06
    .Companion
    0.06
     каждого
    0.06
     производства
    0.06
    _FIRE
    0.06
    Act Density 0.093%

    No Known Activations