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

    Neuronpedia

    INDEX
    Explanations

    French welcome and song titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relevant
    0.65
     Relevant
    0.57
     alınd
    0.57
     citizens
    0.56
     critical
    0.56
     E
    0.55
     মাহ
    0.54
    儿
    0.54
     relevantes
    0.54
    relevant
    0.53
    POSITIVE LOGITS
    㣱
    0.76
     obliv
    0.74
    <unused615>
    0.73
    expandindo
    0.73
     winger
    0.71
     Incub
    0.70
     exhausts
    0.70
     anteriormente
    0.69
    édéric
    0.69
     acreditar
    0.69
    Act Density 0.000%

    No Known Activations