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

    Neuronpedia

    INDEX
    Explanations

    Switching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     publicKey
    -0.07
     Bosnia
    -0.06
     свеж
    -0.06
     combat
    -0.06
    TextArea
    -0.06
    growth
    -0.06
    -sector
    -0.06
    .worker
    -0.06
     Packages
    -0.06
    .digest
    -0.06
    POSITIVE LOGITS
    .updated
    0.08
    )!↵
    0.07
    الإ
    0.07
    ...)↵↵
    0.06
    ]-->↵
    0.06
    ميل
    0.06
    rious
    0.06
    екс
    0.06
    ']");↵
    0.06
     prosec
    0.06
    Act Density 0.026%

    No Known Activations