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

    Neuronpedia

    INDEX
    Explanations

    political and historical ideologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    plik
    1.09
    ởi
    1.09
     Futuristic
    1.08
     hyperplane
    1.07
     tutt
    1.07
     chuột
    1.06
    ؤول
    1.06
     voire
    1.06
    νας
    1.05
     攵
    1.05
    POSITIVE LOGITS
    лм
    1.12
    tól
    1.06
     број
    1.03
    ochlor
    1.01
    ată
    1.00
    ح
    1.00
     영향을
    1.00
    וכ
    0.99
    𝗣
    0.97
    িক
    0.97
    Act Density 0.001%

    No Known Activations