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

    Neuronpedia

    INDEX
    Explanations

    closing brace

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ured
    0.83
    ↵↵↵
    0.66
    (),
    0.65
     herbicides
    0.61
    𝗎
    0.59
     Humber
    0.59
     systém
    0.59
     Hand
    0.59
    Hand
    0.58
     तुरु
    0.58
    POSITIVE LOGITS
    araf
    0.84
     boz
    0.80
    :+
    0.78
     Viejo
    0.76
    :~
    0.74
    ansı
    0.73
    ílio
    0.72
    anjang
    0.72
    ToObject
    0.69
    anesulf
    0.69
    Act Density 0.005%

    No Known Activations