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

    Neuronpedia

    INDEX
    Explanations

    commands and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Expt
    0.47
    Acknowledgement
    0.43
    Hence
    0.41
    良い
    0.41
    osate
    0.39
     Planta
    0.39
    ogramDetails
    0.38
     salient
    0.38
     انتہائی
    0.38
    راتكم
    0.38
    POSITIVE LOGITS
     wich
    0.81
     informations
    0.75
     oder
    0.73
     standart
    0.72
     founded
    0.69
     witch
    0.68
     procent
    0.63
     womans
    0.63
     lenght
    0.61
     acces
    0.61
    Act Density 0.039%

    No Known Activations