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

    Neuronpedia

    INDEX
    Explanations

    references to confirmed issues or bugs in a technical context

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

    Long lines of dashes

    np_acts-logits-general · gemini-2.0-flash

    ages at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.58
    qJ
    -0.51
    antMatchers
    -0.50
    caccio
    -0.50
    irvana
    -0.50
    istö
    -0.50
     fonder
    -0.49
    āju
    -0.49
    ########.
    -0.49
     gela
    -0.49
    POSITIVE LOGITS
    +#+#
    0.72
    󠁢
    0.70
     utafitiHapana
    0.68
     المعيارى
    0.61
     تانيه
    0.60
    ButterKnife
    0.59
    Bakgrunnsstoff
    0.59
    Референце
    0.56
     MainAxisSize
    0.55
     springfox
    0.54
    Act Density 0.462%

    No Known Activations