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

    Neuronpedia

    INDEX
    Explanations

    software, reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Categoria
    -0.07
    単
    -0.07
    ить
    -0.07
     Bene
    -0.07
    #,
    -0.07
    Holy
    -0.07
    -part
    -0.07
    �
    -0.07
     εν
    -0.06
     Comb
    -0.06
    POSITIVE LOGITS
     Γ
    0.06
     İslâm
    0.06
    ver
    0.06
     Hamas
    0.06
     平方
    0.06
    .wik
    0.06
    ,max
    0.06
     isOpen
    0.06
    (rad
    0.06
    ART
    0.06
    Act Density 0.002%

    No Known Activations