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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frozen
    -0.07
     ambigu
    -0.07
     Hans
    -0.07
     Bundle
    -0.07
     duck
    -0.06
    Immutable
    -0.06
     pas
    -0.06
     Judicial
    -0.06
     Glass
    -0.06
     occurred
    -0.06
    POSITIVE LOGITS
    liv
    0.06
     Contr
    0.06
    .tencent
    0.06
     acronym
    0.06
    arken
    0.06
     segregated
    0.06
    Electronic
    0.06
    ulo
    0.06
     scri
    0.06
    paced
    0.06
    Act Density 0.048%

    No Known Activations