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

    Neuronpedia

    INDEX
    Explanations

    Okay, let's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     גם
    0.37
    ρε
    0.36
     каждого
    0.36
     πάντα
    0.36
     sogar
    0.35
    ______________
    0.34
     አይደለም
    0.34
     অন্যরা
    0.34
    によっては
    0.33
     blocks
    0.33
    POSITIVE LOGITS
     privind
    0.52
     regarding
    0.49
     የ
    0.47
     você
    0.42
     penchant
    0.41
     chez
    0.40
     llevar
    0.40
     עבור
    0.40
     Regarding
    0.39
    inetics
    0.38
    Act Density 2.318%

    No Known Activations