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

    Neuronpedia

    INDEX
    Explanations

    bibliographic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    leaf
    0.45
    uncan
    0.43
    ;
    0.42
    ؛
    0.41
    atau
    0.41
    alt
    0.40
    chel
    0.40
    ;
    0.39
    aranam
    0.39
    ätt
    0.38
    POSITIVE LOGITS
     españa
    0.43
     ⏮
    0.43
     JButton
    0.43
     ${(
    0.43
     DirectX
    0.42
     Cancellation
    0.38
    Cancellation
    0.38
    ';"+
    0.38
     अबा
    0.38
    yatiti
    0.38
    Act Density 0.000%

    No Known Activations