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

    Neuronpedia

    INDEX
    Explanations

    creative proposals, controlling behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     earm
    0.42
    အရေ
    0.37
    Allocate
    0.36
    ificaciones
    0.36
     Partially
    0.35
    伸
    0.35
    📞
    0.35
    헷
    0.34
    ποιή
    0.34
    শীল
    0.33
    POSITIVE LOGITS
     ion
    0.44
     Farrell
    0.43
    inho
    0.41
     Lon
    0.40
     Ion
    0.40
    Ion
    0.40
     Dempsey
    0.39
    GetResponse
    0.39
    PGS
    0.39
     Chin
    0.39
    Act Density 0.003%

    No Known Activations