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

    Neuronpedia

    INDEX
    Explanations

    `used`, `sequence`, `label`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    0.82
    θέ
    0.82
     πί
    0.79
     λογ
    0.78
    mins
    0.75
    ილი
    0.75
    er
    0.74
     በመ
    0.74
    λ
    0.74
    zust
    0.73
    POSITIVE LOGITS
    шает
    0.88
     sequence
    0.77
     inspired
    0.74
     fosters
    0.71
     copyrighted
    0.68
     regarding
    0.67
     exerts
    0.66
    像
    0.66
     agencies
    0.66
     recalling
    0.66
    Act Density 0.001%

    No Known Activations