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

    Neuronpedia

    INDEX
    Explanations

    characteristics of qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.84
    Caracter
    0.84
    Character
    0.79
    Р
    0.78
    $
    0.75
     것이다
    0.74
    oints
    0.73
     харак
    0.71
    Cells
    0.70
    Ч
    0.70
    POSITIVE LOGITS
    il
    1.20
    ே
    1.16
    ie
    1.11
    y
    1.10
    на
    1.05
    िन
    0.96
    ين
    0.95
    ва
    0.94
    ี
    0.93
    ни
    0.89
    Act Density 0.008%

    No Known Activations