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

    Neuronpedia

    INDEX
    Explanations

    code constructs and data formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     או
    0.52
     και
    0.50
    และการ
    0.49
    ALL
    0.48
    inicio
    0.46
    度和
    0.46
     ή
    0.46
     বা
    0.45
     તમામ
    0.45
    정과
    0.45
    POSITIVE LOGITS
     sogenannte
    0.62
     sogen
    0.59
     sogenannten
    0.52
     tiny
    0.48
     cosidd
    0.47
     cuyo
    0.46
     cuya
    0.46
     tarafından
    0.45
     wodurch
    0.45
     cleverly
    0.44
    Act Density 0.063%

    No Known Activations