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

    Neuronpedia

    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .iso
    -0.07
    person
    -0.07
    lore
    -0.07
    局副局长
    -0.07
    ."""↵↵
    -0.07
    (predict
    -0.07
    ≏
    -0.07
     jspb
    -0.07
    istence
    -0.06
    roadcast
    -0.06
    POSITIVE LOGITS
     Höhe
    0.08
    ローン
    0.08
     país
    0.07
    ´
    0.07
     meses
    0.07
    決定
    0.07
     época
    0.07
    ROW
    0.07
    _fe
    0.07
    цу
    0.06
    Act Density 0.008%

    No Known Activations