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

    Neuronpedia

    INDEX
    Explanations

    f starter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जनता
    0.68
    aktor
    0.65
    actor
    0.63
     enter
    0.63
    ield
    0.60
     बनते
    0.60
     बनती
    0.59
    leet
    0.59
    ashion
    0.58
    机
    0.58
    POSITIVE LOGITS
     F
    0.77
    اندان
    0.70
    ables
    0.70
    IVES
    0.69
    觜
    0.69
     famine
    0.68
    hydrox
    0.68
    êng
    0.68
    F
    0.67
    િવ
    0.67
    Act Density 0.071%

    No Known Activations