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

    Neuronpedia

    INDEX
    Explanations

    method declarations and their parameters in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Opening parentheses followed by type declarations

    np_acts-logits-general · gemini-2.0-flash

    programming data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.68
     שוליים
    -0.66
    <?
    -0.64
    /*
    -0.61
    expandindo
    -0.59
     joaat
    -0.58
     NDL
    -0.57
    Espèce
    -0.54
     mxArray
    -0.52
     henvisninger
    -0.51
    POSITIVE LOGITS
     tromper
    0.61
     larmes
    0.57
     vôtre
    0.56
    complexContent
    0.55
    UnsafeEnabled
    0.53
     jambes
    0.52
     jambe
    0.52
     fumée
    0.51
     mahdol
    0.51
     aukš
    0.51
    Act Density 0.017%

    No Known Activations