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

    Neuronpedia

    INDEX
    Explanations

    elements of mathematical notation or formatting

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

    latex newline commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.66
    ↵↵↵
    -0.49
    <eos>
    -0.48
    1
    -0.44
    The
    -0.43
    ↵↵↵↵
    -0.43
    0
    -0.43
     
    -0.42
    4
    -0.42
    6
    -0.42
    POSITIVE LOGITS
     Infórmanos
    0.89
     '\\;'
    0.88
     Мексичка
    0.87
     nakalista
    0.86
     ujednoznacz
    0.86
    ⟬
    0.84
    sizeCache
    0.84
     gynhyrchwyd
    0.82
     Italijani
    0.80
     surla
    0.79
    Act Density 0.041%

    No Known Activations