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

    Neuronpedia

    INDEX
    Explanations

    until

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ア
    -0.07
     depot
    -0.07
    _world
    -0.07
     ア
    -0.07
     Accord
    -0.07
    🇦
    -0.07
    ía
    -0.07
    erna
    -0.07
     across
    -0.07
    둥
    -0.07
    POSITIVE LOGITS
    ()?.
    0.09
    _bindings
    0.07
    realm
    0.07
     Publishers
    0.07
    draft
    0.07
    .branch
    0.06
    predictions
    0.06
     Narrative
    0.06
    /count
    0.06
     chrom
    0.06
    Act Density 0.009%

    No Known Activations