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

    Neuronpedia

    INDEX
    Explanations

    structured academic writing that discusses findings or analyses

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

    Sections introducing a topic

    np_acts-logits-general · gemini-2.0-flash

    in this section we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.53
     chng
    -0.52
     béo
    -0.47
     елның
    -0.46
    mybatisplus
    -0.46
    ódó
    -0.46
     صوتيه
    -0.45
    ReusableCell
    -0.45
    Obrázky
    -0.45
     Pesquisa
    -0.45
    POSITIVE LOGITS
    ocusing
    0.70
     focus
    0.67
     focuses
    0.67
     discusses
    0.66
    brief
    0.65
     Focusing
    0.65
     focusing
    0.64
     focussing
    0.63
     discus
    0.62
    ここでは
    0.61
    Act Density 0.348%

    No Known Activations