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

    Neuronpedia

    INDEX
    Explanations

    method parameters and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    櫂
    0.40
     استخدام
    0.35
    щин
    0.35
    ißler
    0.35
    ళ్ళ
    0.34
    oleic
    0.34
     استخدم
    0.33
     Solubility
    0.32
     riffs
    0.32
    લમાં
    0.31
    POSITIVE LOGITS
    context
    0.41
     _:
    0.36
    BuildContext
    0.35
    args
    0.32
    env
    0.32
     ...
    0.32
     EventArgs
    0.31
     context
    0.31
    event
    0.31
     контек
    0.31
    Act Density 0.018%

    No Known Activations