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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical and biological processes

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

    technical terms or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commercial
    -0.54
    setVerticalGroup
    -0.52
    _',
    -0.50
    @",
    -0.49
     private
    -0.49
     Infórmanos
    -0.48
    *',
    -0.47
    ':
    -0.47
    новниш
    -0.47
    "},
    -0.46
    POSITIVE LOGITS
     is
    0.64
    antaranya
    0.63
     zelve
    0.62
     ciertamente
    0.61
     tarko
    0.60
     enseña
    0.60
     avoient
    0.56
     ontstaan
    0.56
     Tatsache
    0.56
     adquis
    0.56
    Act Density 1.087%

    No Known Activations