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

    Neuronpedia

    INDEX
    Explanations

    Experiments/Observations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mint
    -0.07
     inval
    -0.06
     simult
    -0.06
    監
    -0.06
     безпеки
    -0.06
     annex
    -0.06
     Kabul
    -0.06
    rokes
    -0.06
     Laden
    -0.06
    保证
    -0.06
    POSITIVE LOGITS
    .Mult
    0.07
    .projects
    0.07
    افه
    0.06
    .Now
    0.06
     fscanf
    0.06
    LOW
    0.06
    aining
    0.06
     GHC
    0.06
    _STATIC
    0.06
    тах
    0.06
    Act Density 0.053%

    No Known Activations