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

    Neuronpedia

    INDEX
    Explanations

    code file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ట్స్‌
    0.86
    rooted
    0.83
    ట్స్
    0.81
    myer
    0.77
    ალური
    0.75
    μη
    0.74
    вает
    0.72
     ε
    0.71
    āj
    0.71
     rooting
    0.70
    POSITIVE LOGITS
    다
    1.04
     persones
    1.02
    І
    0.98
     modalités
    0.97
     bloqueo
    0.96
    리
    0.94
     marchandises
    0.93
    izion
    0.91
    ক
    0.89
     médicament
    0.89
    Act Density 0.000%

    No Known Activations