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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications, particularly formatted citations and preprints from arXiv

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

    arXiv astro-ph hep-th

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.79
    windowFixed
    -0.75
    kloped
    -0.71
     Мексичка
    -0.71
    fjspx
    -0.69
     kaarangay
    -0.68
     betweenstory
    -0.67
    msgSender
    -0.67
     AppCompatTheme
    -0.67
     виправивши
    -0.66
    POSITIVE LOGITS
    чева
    0.27
     food
    0.26
     pakan
    0.26
    .
    0.26
     “
    0.25
     hook
    0.25
     kidna
    0.25
     Food
    0.25
     стекла
    0.25
     
    0.24
    Act Density 0.003%

    No Known Activations