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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    それ
    -0.07
     FormsModule
    -0.07
     ücretsiz
    -0.07
     잘못
    -0.07
     pues
    -0.07
     مصر
    -0.07
     Ginny
    -0.07
    基建
    -0.07
     imagin
    -0.07
     POLITICO
    -0.07
    POSITIVE LOGITS
     Throughout
    0.07
    atching
    0.07
    унк
    0.07
    ob
    0.07
     block
    0.07
    Number
    0.07
    _batch
    0.06
    ន
    0.06
    Font
    0.06
     Filter
    0.06
    Act Density 0.003%

    No Known Activations