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

    Neuronpedia

    INDEX
    Explanations

    attributes related to technology and specifications in products

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

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    cameras capture, motor that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !!!!!!!!!!
    -0.76
    !!!!!!!!!
    -0.75
    !!!!!
    -0.73
    !!!!!!
    -0.72
    !!!!!!!!
    -0.70
    !!!!!!!
    -0.70
     !!!!!!
    -0.69
     !!!!!
    -0.68
    !!!"
    -0.68
    !!!!
    -0.66
    POSITIVE LOGITS
     thankfully
    0.70
    прочем
    0.70
     courtesy
    0.67
     thanks
    0.65
     kasarigan
    0.65
     presumably
    0.65
    presumably
    0.64
    RenderAtEndOf
    0.64
     isn
    0.64
    Elsewhere
    0.64
    Act Density 0.275%

    No Known Activations