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

    Neuronpedia

    INDEX
    Explanations

    .NOTES

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     running
    0.41
    ษา
    0.41
     leaving
    0.37
     दोन
    0.37
     permanent
    0.36
     ALS
    0.36
     PSA
    0.36
     temporary
    0.35
     churning
    0.35
     surprise
    0.35
    POSITIVE LOGITS
     remerc
    0.48
    冼
    0.41
    第一個
    0.40
    主張
    0.40
    琙
    0.40
     *=
    0.40
     tijekom
    0.40
     Tijdens
    0.40
     $%
    0.39
     handleSubmit
    0.39
    Act Density 0.001%

    No Known Activations