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

    Neuronpedia

    INDEX
    Explanations

    create or craft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.52
     vai
    0.50
    م
    0.50
     wre
    0.49
    ↵
    0.47
     Saltar
    0.47
     Cependant
    0.46
     vorhanden
    0.45
     nays
    0.45
    |
    0.45
    POSITIVE LOGITS
    likle
    0.56
     ਇੱਕ
    0.54
    famil
    0.50
    knit
    0.50
    TC
    0.50
    FANG
    0.50
    ši
    0.48
    iato
    0.48
    five
    0.47
    mortem
    0.47
    Act Density 0.707%

    No Known Activations