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

    Neuronpedia

    INDEX
    Explanations

    required by your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     muertos
    1.13
     salivary
    1.10
    𝑔
    1.09
    𝑅
    1.09
    𝑣
    1.06
    𝐼
    1.02
    𝑀
    1.01
    𝓌
    0.99
     rebirth
    0.99
    puri
    0.98
    POSITIVE LOGITS
    с
    0.97
    en
    0.96
    d
    0.94
    ла
    0.84
    ड
    0.82
    ा
    0.82
    ない
    0.80
    de
    0.79
    리
    0.79
    े
    0.77
    Act Density 0.008%

    No Known Activations