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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')}↵
    -0.06
     Trader
    -0.06
    acji
    -0.05
    ObjectId
    -0.05
    modelName
    -0.05
    870
    -0.05
    setContent
    -0.05
    Tasks
    -0.05
    Destroy
    -0.05
    '}↵
    -0.05
    POSITIVE LOGITS
    rence
    0.07
     pense
    0.07
    اير
    0.07
     pelo
    0.06
    iciary
    0.06
     Rosenstein
    0.06
    .Source
    0.06
     """
↵
↵
    0.06
    lags
    0.06
     salopes
    0.06
    Act Density 0.130%

    No Known Activations