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

    Neuronpedia

    INDEX
    Explanations

    understanding potential actions or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tattha
    0.47
    聚集
    0.46
     নাব
    0.44
    merzen
    0.43
     थक
    0.43
     Tex
    0.43
     సందర్భ
    0.42
     Puede
    0.41
     Moor
    0.41
    損傷
    0.41
    POSITIVE LOGITS
    N
    0.61
    C
    0.51
    idy
    0.50
    E
    0.49
    Nine
    0.47
    I
    0.47
     astral
    0.46
     instruments
    0.46
    CHT
    0.46
    G
    0.46
    Act Density 0.000%

    No Known Activations