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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sensors
    -0.09
     portfolios
    -0.08
     etkin
    -0.08
    issons
    -0.08
     जिन्होंने
    -0.07
     കാർ
    -0.07
     플
    -0.07
    _RX
    -0.07
    igs
    -0.07
     sensores
    -0.07
    POSITIVE LOGITS
     obligatorio
    0.09
     alphabetical
    0.09
    Requirement
    0.09
    Lastname
    0.09
     redact
    0.09
     uppercase
    0.09
     obrigatório
    0.08
     requisito
    0.08
     obbl
    0.08
     capitalization
    0.08
    Act Density 0.006%

    No Known Activations