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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marvel
    -0.07
    ocations
    -0.07
    _draw
    -0.07
    erus
    -0.07
    -ex
    -0.07
    osa
    -0.06
     bursting
    -0.06
    국
    -0.06
    φαρ
    -0.06
    ifold
    -0.06
    POSITIVE LOGITS
    ♀♀♀♀
    0.06
     сель
    0.06
    ikk
    0.06
    %p
    0.06
    alach
    0.06
    .Raycast
    0.06
    ){
↵
↵
    0.06
     něho
    0.06
     زیرا
    0.06
     toll
    0.06
    Act Density 0.010%

    No Known Activations