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

    Neuronpedia

    INDEX
    Explanations

    Instruction, Human, Question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FRI
    0.47
     самой
    0.45
     tych
    0.44
     essen
    0.43
     Koch
    0.42
    anything
    0.41
     nedeni
    0.41
    friends
    0.40
    after
    0.40
     taux
    0.40
    POSITIVE LOGITS
    Purpose
    0.49
     Purpose
    0.48
    प्रिल
    0.46
     준비
    0.45
     목적
    0.44
    脚本
    0.44
     问题
    0.43
     목
    0.42
    Question
    0.41
     작성
    0.41
    Act Density 0.004%

    No Known Activations