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

    Neuronpedia

    INDEX
    Explanations

    definition of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     backlash
    0.40
     puk
    0.40
     rowIndex
    0.38
     kind
    0.38
     dig
    0.38
     Vito
    0.37
    subseteq
    0.37
     back
    0.37
     conce
    0.36
     JsonSerializer
    0.36
    POSITIVE LOGITS
    лося
    0.43
    ayit
    0.43
     narration
    0.41
     непри
    0.40
    ্ঞ
    0.39
    SHARE
    0.39
    ধারা
    0.38
    दारा
    0.38
    atthakath
    0.38
    अप्र
    0.37
    Act Density 0.003%

    No Known Activations