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

    Neuronpedia

    INDEX
    Explanations

    list of tasks or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     singkat
    0.49
     costi
    0.47
     Cala
    0.46
     note
    0.46
     comment
    0.44
     cái
    0.44
     Keaton
    0.44
     cath
    0.44
     T
    0.44
     Lauren
    0.43
    POSITIVE LOGITS
     undivided
    0.50
    ައ
    0.50
    سرائيل
    0.44
    ->__
    0.44
    izr
    0.42
     manuscripts
    0.42
    odend
    0.42
    inados
    0.41
     Manuscripts
    0.41
     niezb
    0.40
    Act Density 0.003%

    No Known Activations