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

    Neuronpedia

    INDEX
    Explanations

    minimum requirements or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ආ
    0.44
     usamos
    0.44
     analges
    0.41
     refuer
    0.40
     বিস্ম
    0.39
     carcinogenesis
    0.38
     defesa
    0.38
     tuvimos
    0.37
     malah
    0.36
     utilizamos
    0.36
    POSITIVE LOGITS
     eligible
    0.73
    少なくとも
    0.71
     almeno
    0.70
    至少
    0.68
     কমপক্ষে
    0.65
     sufficiently
    0.64
     mindestens
    0.64
    具备
    0.62
     compatible
    0.60
    要有
    0.59
    Act Density 0.406%

    No Known Activations