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

    Neuronpedia

    INDEX
    Explanations

    folding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     최대
    -0.08
     يش
    -0.06
     Canton
    -0.06
    eldo
    -0.06
    kd
    -0.06
    izzo
    -0.06
     uží
    -0.06
     templ
    -0.06
     اثر
    -0.06
    704
    -0.06
    POSITIVE LOGITS
    ług
    0.07
    ART
    0.07
    İK
    0.06
    TB
    0.06
     prevention
    0.06
     إل
    0.06
     whit
    0.06
    ıt
    0.06
     KING
    0.06
     Kong
    0.06
    Act Density 0.026%

    No Known Activations