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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or terms, particularly in mathematical or scientific contexts

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

    Mandel, Indian, Landau names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.47
     Wicidata
    -0.46
     Comprometido
    -0.44
    adpleegd
    -0.40
     <>",
    -0.40
     juzg
    -0.39
     säll
    -0.39
    Rüyada
    -0.39
    JsonPropertyName
    -0.38
    Décès
    -0.38
    POSITIVE LOGITS
    andal
    0.76
    endi
    0.73
    andy
    0.72
    ande
    0.71
    ndx
    0.70
     Mandel
    0.70
     Andi
    0.69
    ndal
    0.69
    andan
    0.68
    ondas
    0.68
    Act Density 0.045%

    No Known Activations