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

    Neuronpedia

    INDEX
    Explanations

    life stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    textInput
    -0.07
     idiot
    -0.07
    /task
    -0.07
    杯
    -0.06
     complexion
    -0.06
     взгляд
    -0.06
     forbidden
    -0.06
    اوية
    -0.06
    \Unit
    -0.06
    _array
    -0.06
    POSITIVE LOGITS
    uco
    0.06
    Vis
    0.06
     спеці
    0.06
     أكتوبر
    0.06
    enticator
    0.06
    _pemb
    0.06
     siguiente
    0.06
    Merc
    0.06
    utes
    0.06
    itage
    0.06
    Act Density 0.319%

    No Known Activations