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

    Neuronpedia

    INDEX
    Explanations

    potential or advantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ça
    0.76
     Consensus
    0.70
     freshness
    0.68
    কন
    0.68
    FED
    0.64
    笠
    0.64
     Article
    0.64
     consenso
    0.64
     চাহিয়া
    0.63
     Ways
    0.62
    POSITIVE LOGITS
     retorted
    0.78
    ดิน
    0.71
    冒
    0.70
    ྩ
    0.66
    ﻬ
    0.66
    擘
    0.65
     hain
    0.64
    肢
    0.64
    INPUT
    0.63
    nder
    0.62
    Act Density 0.000%

    No Known Activations