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

    Neuronpedia

    INDEX
    Explanations

    specific product specifications and comparisons in technology discussions

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

    Tokens after named entities/acronyms

    np_acts-logits-general · gemini-2.0-flash

    OxyContin | MSA | ubuntu | Amazon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.81
    ormais
    -0.75
     ainfi
    -0.70
     quæ
    -0.67
    ]),
    -0.67
     varandra
    -0.64
     iſt
    -0.64
    ’”
    -0.63
    NUMX
    -0.62
     sahiptir
    -0.62
    POSITIVE LOGITS
     stuff
    1.07
     thing
    0.95
     anyway
    0.90
     though
    0.89
     too
    0.85
     guys
    0.84
     etc
    0.84
     thingy
    0.83
     anyways
    0.83
     because
    0.81
    Act Density 0.690%

    No Known Activations