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

    Neuronpedia

    INDEX
    Explanations

    pointer dereferencing and memory allocation patterns in code

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

    pointer dereference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     müſſen
    -0.71
     zoude
    -0.70
    iſchen
    -0.68
    ésultats
    -0.67
     Autorisations
    -0.66
    niſſe
    -0.65
    ſehen
    -0.65
    enablog
    -0.64
     laſſen
    -0.63
    onghi
    -0.63
    POSITIVE LOGITS
     *
    0.69
    *
    0.69
    (*
    0.64
     *++
    0.57
    *@
    0.54
    #*
    0.52
     *((
    0.51
     *@
    0.49
     (*
    0.48
    -*
    0.46
    Act Density 0.006%

    No Known Activations