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

    Neuronpedia

    INDEX
    Explanations

    programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fucking
    0.55
     betray
    0.50
    worldly
    0.49
    wtf
    0.48
    defence
    0.47
     behest
    0.47
     nihil
    0.47
    ٸ
    0.46
     betrayal
    0.45
     इन्हे
    0.44
    POSITIVE LOGITS
    学生的
    0.50
     eléct
    0.47
    教师
    0.47
     STUDENT
    0.47
    0.47
     кисло
    0.46
     accumulator
    0.46
     Computing
    0.46
    럏
    0.45
    觕
    0.45
    Act Density 0.018%

    No Known Activations