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

    Neuronpedia

    INDEX
    Explanations

    programming and logic contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     регу
    0.52
    BackButton
    0.50
    αλλ
    0.49
     цель
    0.48
    ının
    0.48
    าล
    0.47
     його
    0.47
    正则
    0.46
     выпусти
    0.46
    ız
    0.46
    POSITIVE LOGITS
     str
    0.49
    ن
    0.47
    SEX
    0.47
     sd
    0.46
     ESTIM
    0.45
    シ
    0.45
    SD
    0.45
     hollow
    0.45
     VT
    0.45
     on
    0.45
    Act Density 0.000%

    No Known Activations