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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Re
    -0.06
    ylum
    -0.06
    theon
    -0.06
     hard
    -0.06
    aspberry
    -0.06
    .Dto
    -0.06
    spawn
    -0.06
    Dark
    -0.06
    Dynamic
    -0.06
    ffb
    -0.06
    POSITIVE LOGITS
     Spears
    0.07
    овий
    0.07
    blah
    0.07
    .GO
    0.06
    341
    0.06
     kah
    0.06
     Shi
    0.06
     Huckabee
    0.06
     各
    0.06
    \$
    0.06
    Act Density 0.001%

    No Known Activations