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

    Neuronpedia

    INDEX
    Explanations

    based on criteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aiutare
    0.52
     wilfully
    0.47
     ajudar
    0.46
     rebranding
    0.46
     भाषण
    0.46
     apoyar
    0.46
    ями
    0.46
     renaming
    0.46
     که
    0.45
     accesible
    0.45
    POSITIVE LOGITS
    데이터
    0.44
    。《
    0.42
    Settings
    0.41
    Week
    0.41
    炔
    0.41
    给定
    0.41
    ㎜
    0.40
    日期
    0.40
    仅
    0.40
    Sem
    0.40
    Act Density 0.001%

    No Known Activations