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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     triangular
    -0.08
    ぃ
    -0.08
     Grat
    -0.08
     Make
    -0.07
    грамм
    -0.07
     adjusts
    -0.07
    ifference
    -0.07
     geliştir
    -0.07
     ).
    -0.07
    那就是
    -0.07
    POSITIVE LOGITS
     kü
    0.07
    ỷ
    0.07
    �
    0.07
    boy
    0.07
    Evidence
    0.07
    有效期
    0.07
     ton
    0.06
    .elements
    0.06
     ideology
    0.06
    StrictEqual
    0.06
    Act Density 0.109%

    No Known Activations