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

    Neuronpedia

    INDEX
    Explanations

    explaining circumstances or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蓥
    0.55
    p
    0.54
    i
    0.50
    es
    0.50
    ?
    0.49
     ९
    0.46
    f
    0.46
    id
    0.44
    zeichen
    0.43
    মালা
    0.43
    POSITIVE LOGITS
    ያንዳንዱ
    0.56
     backstory
    0.54
     должность
    0.54
     quirk
    0.52
     اہم
    0.51
     चांगली
    0.51
     idiosyncratic
    0.51
    ͆
    0.50
     चांग
    0.50
    дың
    0.49
    Act Density 0.168%

    No Known Activations