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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ”的
    -0.07
     Moh
    -0.07
     نه
    -0.06
    (or
    -0.06
     bail
    -0.06
     Κου
    -0.06
    �
    -0.06
    trap
    -0.06
     Bail
    -0.06
    응
    -0.06
    POSITIVE LOGITS
     anon
    0.07
    illions
    0.07
     Skin
    0.07
    /int
    0.07
     utilize
    0.07
     chiếc
    0.06
     shutil
    0.06
     brows
    0.06
     donating
    0.06
    _skin
    0.06
    Act Density 0.011%

    No Known Activations