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

    Neuronpedia

    INDEX
    Explanations

    contrasting conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᄉ
    0.50
    у
    0.49
    لي
    0.49
    找
    0.47
     hilltop
    0.47
    л
    0.46
    勞
    0.46
     Trench
    0.45
    邈
    0.45
    ManyToMany
    0.44
    POSITIVE LOGITS
     ("
    0.51
     oa
    0.43
     "\
    0.42
     aerodynamic
    0.42
     commencent
    0.42
     dlr
    0.41
     introduced
    0.41
     ('
    0.41
     deze
    0.40
    この
    0.40
    Act Density 0.003%

    No Known Activations