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

    Neuronpedia

    INDEX
    Explanations

    logical operations or specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ikken
    0.43
    åk
    0.41
    ⤥
    0.41
     audioElement
    0.40
     thine
    0.40
     substrings
    0.40
     MDL
    0.39
     Chromatogr
    0.39
     Å
    0.39
     sebuah
    0.38
    POSITIVE LOGITS
    ות
    0.49
    発生
    0.47
    f
    0.47
    學生
    0.47
    פת
    0.44
     လုပ်
    0.44
    值
    0.44
    常用
    0.44
    攻擊
    0.43
    ကြီး
    0.43
    Act Density 0.010%

    No Known Activations