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

    Neuronpedia

    INDEX
    Explanations

    'd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لل
    -0.07
     جریان
    -0.07
    _datasets
    -0.06
     fancy
    -0.06
    алу
    -0.06
    َع
    -0.06
     disables
    -0.06
     emergencies
    -0.06
    Containing
    -0.06
    füh
    -0.06
    POSITIVE LOGITS
    _ARM
    0.06
     Warcraft
    0.06
     Exactly
    0.06
    Carbon
    0.06
     Albert
    0.06
    色的
    0.06
     classNames
    0.06
     btnSave
    0.06
     Wet
    0.06
    -single
    0.06
    Act Density 0.003%

    No Known Activations