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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ometry
    -0.07
    Nature
    -0.07
    Copy
    -0.07
    月底
    -0.07
    .Utility
    -0.07
    שמ
    -0.07
    中东
    -0.07
     NHL
    -0.07
     GFP
    -0.06
    printf
    -0.06
    POSITIVE LOGITS
     standard
    0.07
    {$
    0.07
     davran
    0.07
    _paper
    0.07
    .week
    0.07
     constant
    0.07
    ธนาคาร
    0.06
     ">
    0.06
     userinfo
    0.06
    应收账
    0.06
    Act Density 0.012%

    No Known Activations