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

    Neuronpedia

    INDEX
    Explanations

    Social divisions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tendency
    -0.07
    umed
    -0.06
     labeled
    -0.06
     जब
    -0.06
     PDF
    -0.06
    rd
    -0.06
     comparable
    -0.06
     Xia
    -0.06
     mane
    -0.06
    ्वत
    -0.06
    POSITIVE LOGITS
    Gran
    0.07
    .DeepEqual
    0.07
     chút
    0.07
    _roles
    0.07
    _SOUND
    0.07
    _PENDING
    0.07
     _|
    0.07
    /screen
    0.07
    ($__
    0.07
    ptune
    0.07
    Act Density 0.024%

    No Known Activations