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

    Neuronpedia

    INDEX
    Explanations

    Code and programming context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izio
    -0.07
    간
    -0.07
    early
    -0.06
     Papa
    -0.06
     fourth
    -0.06
    Disabled
    -0.06
    Chicago
    -0.06
    Four
    -0.06
    IFIED
    -0.06
    ट
    -0.06
    POSITIVE LOGITS
    culus
    0.07
    .Month
    0.06
    byter
    0.06
     precios
    0.06
    csrf
    0.06
    jon
    0.06
    を持
    0.06
    �
    0.06
     posX
    0.06
     debilitating
    0.06
    Act Density 0.009%

    No Known Activations