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

    Neuronpedia

    INDEX
    Explanations

    Here are a few options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ссер
    0.42
     گاه
    0.41
     именно
    0.41
     raff
    0.41
     podrían
    0.39
     यांचा
    0.39
     ఇంకా
    0.38
    भोपाल
    0.37
     энерго
    0.37
     focussed
    0.37
    POSITIVE LOGITS
     її
    0.65
     їх
    0.51
     оригі
    0.51
     zastos
    0.50
     і
    0.50
     propon
    0.47
    ribly
    0.46
     vys
    0.46
    Yu
    0.45
    Yak
    0.44
    Act Density 0.007%

    No Known Activations