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

    Neuronpedia

    INDEX
    Explanations

    lack thereof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.44
     سی
    0.44
    یر
    0.40
     mỗi
    0.38
    ین
    0.37
     tử
    0.37
    ヵ
    0.37
    ی
    0.36
     سم
    0.35
     टेंस
    0.35
    POSITIVE LOGITS
    0.47
    శ్
    0.37
     dikutip
    0.36
     unequivocally
    0.35
    ;&
    0.35
     Nuggets
    0.34
     destacan
    0.34
     ponctué
    0.33
     TRACK
    0.33
     gleaned
    0.32
    Act Density 0.027%

    No Known Activations