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

    Neuronpedia

    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cluster
    -0.07
     creado
    -0.07
    _WS
    -0.07
    clamation
    -0.07
    decode
    -0.07
    ández
    -0.06
    SmartPointer
    -0.06
     пла
    -0.06
    ния
    -0.06
     binaries
    -0.06
    POSITIVE LOGITS
    isContained
    0.07
    Report
    0.07
    0.07
    Evento
    0.06
    getDate
    0.06
    	Label
    0.06
    ainen
    0.06
    Hair
    0.06
     bunny
    0.06
    _putstr
    0.06
    Act Density 0.004%

    No Known Activations