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

    Neuronpedia

    INDEX
    Explanations

    wave functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gamers
    -0.08
     пров
    -0.07
    ोजन
    -0.07
    CEEDED
    -0.07
    nect
    -0.06
     usage
    -0.06
    ических
    -0.06
     다운받
    -0.06
    ункт
    -0.06
     SCAN
    -0.06
    POSITIVE LOGITS
     fscanf
    0.07
    kf
    0.07
    .person
    0.07
    .recipe
    0.07
     Combined
    0.06
     forever
    0.06
     paddingRight
    0.06
    .extent
    0.06
     Bennett
    0.06
     إل
    0.06
    Act Density 0.015%

    No Known Activations