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

    Neuronpedia

    INDEX
    Explanations

    academic subjects and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    钝
    0.45
    ্লিষ্ট
    0.38
     Withers
    0.37
    세계
    0.37
    沏
    0.37
    未来的
    0.36
    Discuss
    0.36
    視野
    0.36
    坠
    0.35
    ТР
    0.35
    POSITIVE LOGITS
     anthropological
    0.53
     anthropologist
    0.50
     Funktion
    0.47
     anthropology
    0.46
     sociologist
    0.45
     antrop
    0.44
     Anthropology
    0.44
     anthropologists
    0.44
    funktion
    0.42
    ത്തിലൂടെ
    0.41
    Act Density 0.000%

    No Known Activations