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

    Neuronpedia

    INDEX
    Explanations

    layered system or approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.43
     on
    0.43
     branches
    0.42
    Besides
    0.41
    ॒
    0.41
    ৩
    0.40
     branch
    0.40
     contributor
    0.40
    Computation
    0.40
     করি
    0.39
    POSITIVE LOGITS
     patip
    0.50
     టిప్పు
    0.47
    DepartTime
    0.46
    fromj
    0.45
    gäng
    0.44
     слот
    0.44
     trophies
    0.44
     hazelnuts
    0.44
    amnă
    0.44
     haki
    0.43
    Act Density 0.002%

    No Known Activations