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

    Neuronpedia

    INDEX
    Explanations

    US political figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OEt
    0.71
     OMX
    0.71
    祗
    0.70
    Bombay
    0.70
     alkaline
    0.70
     Bons
    0.69
    വാസ
    0.69
    ParameterActive
    0.68
     artesan
    0.68
     Catawiki
    0.68
    POSITIVE LOGITS
     Trump
    2.26
    Trump
    2.08
     Biden
    2.07
    Biden
    1.79
     Donald
    1.76
    特朗普
    1.69
    Donald
    1.55
     Republicans
    1.52
     ट्रंप
    1.50
     Democrats
    1.48
    Act Density 0.149%

    No Known Activations