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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements in code snippets

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

    space between words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    engkapi
    -0.38
     Empfang
    -0.34
     Comunicación
    -0.33
    ">${
    -0.32
     Handwerk
    -0.32
     órdenes
    -0.32
     Naciones
    -0.32
    andangan
    -0.32
     composición
    -0.31
    >{@
    -0.31
    POSITIVE LOGITS
     space
    0.85
    space
    0.77
     Space
    0.75
    SPACE
    0.71
     spaces
    0.70
     Spaces
    0.68
    Space
    0.68
     SPACE
    0.66
    spaces
    0.66
    Spaces
    0.66
    Act Density 0.336%

    No Known Activations