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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نان
    -0.06
     Invent
    -0.06
    увалися
    -0.06
     Dont
    -0.06
     mpg
    -0.06
    .games
    -0.06
    lararası
    -0.06
     aerobic
    -0.06
     Hydra
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ,},↵
    0.07
     ',',
    0.07
    .Named
    0.06
    sume
    0.06
     Miss
    0.06
     proliferation
    0.06
    画
    0.06
    asure
    0.06
     Chunk
    0.06
    _MM
    0.06
    Act Density 0.050%

    No Known Activations