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

    Neuronpedia

    INDEX
    Explanations

    bronze, bronzer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Menurut
    0.95
     Wochen
    0.94
     zegt
    0.94
    Algun
    0.94
     вероят
    0.93
    atória
    0.93
    gub
    0.93
    positivo
    0.92
    wna
    0.91
    ام
    0.91
    POSITIVE LOGITS
     ovaries
    0.98
     aisles
    0.92
     duplicates
    0.85
    們
    0.85
     contents
    0.83
     cupboards
    0.82
     duties
    0.82
     precursors
    0.81
     consonants
    0.80
     rest
    0.79
    Act Density 0.002%

    No Known Activations