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

    Neuronpedia

    INDEX
    Explanations

    mathematical patterns and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Brains
    -0.07
    .numero
    -0.07
     güneş
    -0.07
    筲
    -0.07
    蔫
    -0.07
     Placement
    -0.07
     katılım
    -0.06
    .magic
    -0.06
    moon
    -0.06
    nym
    -0.06
    POSITIVE LOGITS
     referred
    0.07
    IntegerField
    0.07
     Ref
    0.07
    四种
    0.07
     Revolution
    0.07
     Cynthia
    0.07
    上诉
    0.06
    TR
    0.06
    -input
    0.06
    定律
    0.06
    Act Density 0.009%

    No Known Activations