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

    Neuronpedia

    INDEX
    Explanations

    starting with relatively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     కళ
    0.43
     Lugo
    0.39
     ልዩ
    0.39
    价值观
    0.36
    糟
    0.36
     Giacomo
    0.35
     ගැ
    0.35
     யார்
    0.35
     Эн
    0.34
     инженер
    0.34
    POSITIVE LOGITS
     minist
    0.43
    pred
    0.43
     best
    0.41
    forums
    0.40
    pm
    0.40
     Pred
    0.40
    Pred
    0.40
     finest
    0.40
     lind
    0.40
     conting
    0.39
    Act Density 0.000%

    No Known Activations