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

    Neuronpedia

    INDEX
    Explanations

    use word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sido
    0.63
     contrace
    0.62
    ಯು
    0.56
     greatest
    0.54
     extensively
    0.53
     পাশাপাশি
    0.52
     Secara
    0.52
    ′
    0.52
    ぜひ
    0.51
     znan
    0.50
    POSITIVE LOGITS
    nobyl
    0.55
    𝒟
    0.53
     EARL
    0.53
    จุบัน
    0.52
    𝒜
    0.52
     excepción
    0.51
    𝒮
    0.50
    ν
    0.50
    ठबंधन
    0.50
    ли
    0.49
    Act Density 0.086%

    No Known Activations