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

    Neuronpedia

    INDEX
    Explanations

    write a [type of content]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.49
    ,
    0.49
    \
    0.47
     on
    0.47
     {
    0.45
     of
    0.45
    0.44
    ，
    0.43
     a
    0.42
    ers
    0.40
    POSITIVE LOGITS
     patitth
    0.42
     vacanam
    0.39
    ריה
    0.39
     gamanam
    0.38
     adhipp
    0.38
     vutto
    0.37
     perspici
    0.37
     indoct
    0.36
    ገልግሎ
    0.36
     económ
    0.36
    Act Density 0.226%

    No Known Activations