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

    Neuronpedia

    INDEX
    Explanations

    python code or scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Czechoslovak
    0.38
    ବା
    0.36
     похађа
    0.36
    ariyam
    0.36
    DummyView
    0.35
    ctxt
    0.35
    堬
    0.34
    isChecked
    0.34
    வ்வாற
    0.34
     বাংলাদেশী
    0.33
    POSITIVE LOGITS
    语言
    0.59
    語言
    0.56
     language
    0.56
     nyelv
    0.54
     script
    0.53
    代码
    0.50
    language
    0.50
     code
    0.47
     proficiency
    0.45
    anguage
    0.44
    Act Density 0.039%

    No Known Activations