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

    Neuronpedia

    INDEX
    Explanations

    West followed by place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ugy
    0.72
     अभिगमन
    0.71
    इंडियन
    0.69
    ACKS
    0.68
     embraces
    0.65
     gefunden
    0.65
     pradesh
    0.65
    ρει
    0.63
    dataloader
    0.63
    ousal
    0.63
    POSITIVE LOGITS
     Brain
    0.82
     Olive
    0.76
     deixar
    0.72
    姐姐
    0.71
    Brain
    0.70
    kol
    0.70
     દુ
    0.70
     इमो
    0.69
    ogloss
    0.68
     מז
    0.68
    Act Density 0.002%

    No Known Activations