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

    Neuronpedia

    INDEX
    Explanations

    Factors influencing outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    patial
    -0.08
    -cal
    -0.07
    юдж
    -0.07
     docker
    -0.07
     vibes
    -0.06
     debian
    -0.06
    UD
    -0.06
    hoff
    -0.06
    оке
    -0.06
     simulated
    -0.06
    POSITIVE LOGITS
    uchsia
    0.07
     콘
    0.06
     countert
    0.06
    AllArgsConstructor
    0.06
     dort
    0.06
     accordion
    0.06
     ．
    0.06
    "bytes
    0.06
    (flag
    0.06
     ambition
    0.06
    Act Density 0.284%

    No Known Activations