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

    Neuronpedia

    INDEX
    Explanations

    command as, down the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pow
    0.49
    em
    0.48
    Think
    0.46
    Call
    0.45
    Reviews
    0.45
    Alpha
    0.44
    Ken
    0.44
    Brussels
    0.44
    Symbol
    0.42
    Chapter
    0.42
    POSITIVE LOGITS
     hmot
    0.56
     аутох
    0.54
    itabbo
    0.52
    দিগের
    0.52
    myTransform
    0.51
     aislado
    0.51
     ప్రి
    0.51
     zdrav
    0.50
     ಆಹಾರ
    0.50
     benessere
    0.50
    Act Density 0.000%

    No Known Activations