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

    Neuronpedia

    INDEX
    Explanations

    Technical Documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glad
    -0.07
    笱
    -0.07
    /google
    -0.07
    ardi
    -0.07
    兰
    -0.07
    国王
    -0.07
     потребител
    -0.07
     Epstein
    -0.07
    -0.07
     flashing
    -0.07
    POSITIVE LOGITS
    펐
    0.06
     annonces
    0.06
    אוקט
    0.06
     wh
    0.06
    .parametrize
    0.06
    alties
    0.06
    镦
    0.06
    Ԍ
    0.06
    _WORDS
    0.06
    itar
    0.06
    Act Density 0.446%

    No Known Activations