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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vos
    -0.07
    ante
    -0.07
    Andre
    -0.07
    .WaitFor
    -0.07
     marg
    -0.07
    ϋ
    -0.07
     requiring
    -0.07
    anches
    -0.06
     Sant
    -0.06
    ฟ
    -0.06
    POSITIVE LOGITS
     것이다
    0.08
    pollo
    0.07
     tidak
    0.07
    _true
    0.07
     BELOW
    0.07
    Implicit
    0.07
     numpy
    0.07
     함수
    0.06
     strncpy
    0.06
    LAB
    0.06
    Act Density 0.004%

    No Known Activations