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

    Neuronpedia

    INDEX
    Explanations

    Shipping Companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .wav
    -0.07
    =explode
    -0.07
     pigs
    -0.06
    ider
    -0.06
    IPH
    -0.06
    Sharp
    -0.06
    cker
    -0.06
    isma
    -0.06
    -sensitive
    -0.06
    /rec
    -0.06
    POSITIVE LOGITS
    .async
    0.06
     برگ
    0.06
    )';↵
    0.06
     Device
    0.06
    _Status
    0.06
    azı
    0.06
    assert
    0.06
    ceed
    0.06
     steering
    0.06
    เ�
    0.06
    Act Density 0.017%

    No Known Activations