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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    056
    -0.07
     Blender
    -0.07
     Willie
    -0.06
     balances
    -0.06
     smoothed
    -0.06
     opposing
    -0.06
    status
    -0.06
    Downloading
    -0.06
    NotFoundException
    -0.06
    addle
    -0.06
    POSITIVE LOGITS
    beit
    0.06
    엄
    0.06
     nä
    0.06
    ็ต
    0.06
     seguint
    0.06
    işi
    0.06
     cyclist
    0.06
     amatør
    0.06
     lieu
    0.06
     تلك
    0.06
    Act Density 0.007%

    No Known Activations