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

    Neuronpedia

    INDEX
    Explanations

    previously had or created

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pt
    0.54
    ल
    0.52
    ag
    0.46
     xhrObj
    0.44
    ib
    0.44
    j
    0.43
     objectivity
    0.42
    agar
    0.42
    screen
    0.42
     सेल
    0.41
    POSITIVE LOGITS
    ці
    0.52
    міна
    0.52
    тна
    0.50
    运用
    0.48
    දා
    0.48
     می‌شوند
    0.48
     possibilità
    0.47
    да
    0.47
     réalisé
    0.46
     coût
    0.46
    Act Density 0.000%

    No Known Activations