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

    Neuronpedia

    INDEX
    Explanations

    latex amsmath package

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     counters
    0.42
     am
    0.41
     Amos
    0.41
     Amherst
    0.41
    zmdi
    0.40
    System
    0.38
    counter
    0.38
    Am
    0.38
    Counter
    0.38
     counter
    0.38
    POSITIVE LOGITS
     declaring
    0.56
     declares
    0.53
     Declare
    0.53
     deklar
    0.52
     środow
    0.51
     Declar
    0.51
     çevre
    0.50
     dichiar
    0.49
     Decl
    0.48
     environnement
    0.47
    Act Density 0.000%

    No Known Activations