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

    Neuronpedia

    INDEX
    Explanations

    transcription

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有意思
    -0.07
    otor
    -0.07
    נושא
    -0.07
    .match
    -0.07
    interp
    -0.07
    옮
    -0.06
     worrying
    -0.06
     physicist
    -0.06
     opt
    -0.06
    暑期
    -0.06
    POSITIVE LOGITS
    clé
    0.08
    _safe
    0.07
    idences
    0.07
    hani
    0.07
     sabotage
    0.07
     contamination
    0.07
     registrations
    0.07
    用水
    0.07
     CRUD
    0.07
    uations
    0.07
    Act Density 0.003%

    No Known Activations