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

    Neuronpedia

    INDEX
    Explanations

    Singleton design pattern

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    how
    -0.07
    胥
    -0.07
     startTime
    -0.07
    >Last
    -0.07
    ído
    -0.07
     when
    -0.07
    �
    -0.07
    ynthesis
    -0.07
     dó
    -0.06
    _Form
    -0.06
    POSITIVE LOGITS
     Film
    0.07
     desk
    0.07
    acists
    0.07
    ARDS
    0.07
    🌪
    0.06
    _code
    0.06
     Psychiat
    0.06
     Sick
    0.06
    �
    0.06
    בור
    0.06
    Act Density 0.032%

    No Known Activations