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

    Neuronpedia

    INDEX
    Explanations

    psychology, emotion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EXISTS
    -0.07
    YSTICK
    -0.07
     E
    -0.07
     permanently
    -0.06
    _Vert
    -0.06
    人民
    -0.06
    igrated
    -0.06
    G
    -0.06
     Creek
    -0.06
    เม
    -0.06
    POSITIVE LOGITS
     імен
    0.07
     moh
    0.06
    Merge
    0.06
     dyn
    0.06
     men
    0.06
     jorn
    0.06
    284
    0.06
    [tmp
    0.06
     extraordinarily
    0.06
     материал
    0.06
    Act Density 0.033%

    No Known Activations