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

    Neuronpedia

    INDEX
    Explanations

    text formatting elements like ** and \*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     গিয়
    0.41
     ইয়
    0.39
     обл
    0.39
     Amid
    0.37
     voic
    0.36
    atlan
    0.36
    Sea
    0.35
    itic
    0.35
     astrocyte
    0.34
    檯
    0.34
    POSITIVE LOGITS
     chcesz
    0.47
    赠
    0.42
     "*************"
    0.42
    収集
    0.42
     "-----
    0.39
    anwhile
    0.39
     मेघ
    0.37
    ›
    0.37
     zwy
    0.36
     verzek
    0.36
    Act Density 0.000%

    No Known Activations