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

    Neuronpedia

    INDEX
    Explanations

    as of date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    中的
    0.44
    としては
    0.43
     goal
    0.42
     estando
    0.41
    కీ
    0.40
    为一个
    0.40
    作为
    0.40
     brat
    0.40
    作為
    0.39
    那个
    0.38
    POSITIVE LOGITS
     evidenced
    0.48
     denoted
    0.48
     gleaned
    0.45
     pursued
    0.44
     aswell
    0.44
     championed
    0.43
     testified
    0.43
     attested
    0.43
     dictated
    0.42
     Taft
    0.42
    Act Density 0.029%

    No Known Activations