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

    Neuronpedia

    INDEX
    Explanations

    explaining concepts or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     éché
    0.54
    ↵
    0.53
    weg
    0.52
    ↵↵↵
    0.50
     Stur
    0.48
    apsack
    0.47
     Alipay
    0.47
    luster
    0.47
    驅
    0.46
    ifie
    0.46
    POSITIVE LOGITS
     orbits
    0.50
     ported
    0.48
    रा
    0.47
     and
    0.47
    েনারেল
    0.47
     coef
    0.47
     spearheaded
    0.46
     across
    0.45
     orbiting
    0.45
     rightfully
    0.45
    Act Density 0.000%

    No Known Activations