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

    Neuronpedia

    INDEX
    Explanations

    holograms and images

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    測
    -0.07
    .editor
    -0.06
    �
    -0.06
    iesen
    -0.06
     swords
    -0.06
    Quiet
    -0.06
    聖
    -0.06
    aur
    -0.06
     Yoga
    -0.05
     české
    -0.05
    POSITIVE LOGITS
    _INC
    0.07
     Figures
    0.07
     {?}
    0.06
    .views
    0.06
    _nc
    0.06
    /$',
    0.06
    RC
    0.06
    енти
    0.06
    @pytest
    0.06
     лекар
    0.06
    Act Density 0.040%

    No Known Activations