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

    Neuronpedia

    INDEX
    Explanations

    financial or technical metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     алыңыз
    0.46
     stelle
    0.43
     ihm
    0.42
     allen
    0.42
     przec
    0.41
     LN
    0.41
     Coh
    0.41
    opod
    0.41
     saman
    0.41
    遉
    0.40
    POSITIVE LOGITS
    դ
    0.46
     hometown
    0.45
     х
    0.45
    ם
    0.44
    蠻
    0.44
    assies
    0.44
    ハ
    0.44
    ו
    0.44
     affections
    0.44
    nutrition
    0.43
    Act Density 0.001%

    No Known Activations