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

    Neuronpedia

    INDEX
    Explanations

    asking for context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rails
    0.49
     scenarios
    0.44
    羡慕
    0.41
     JPEG
    0.40
     edu
    0.39
    ίο
    0.39
    鲜
    0.39
     entour
    0.38
    eting
    0.38
    嫌
    0.38
    POSITIVE LOGITS
    woman
    0.49
     nakon
    0.49
     fabricante
    0.49
    -
    0.48
    anova
    0.47
    yani
    0.47
    posição
    0.46
     domicilio
    0.46
    ônia
    0.45
     dhammo
    0.45
    Act Density 0.002%

    No Known Activations