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

    Neuronpedia

    INDEX
    Explanations

    attributes and parameters defined in programming classes or methods

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

    setting or code ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.85
    '],$
    -0.75
    enterOuterAlt
    -0.70
     '{@
    -0.69
     الرياضيه
    -0.67
    "):
    -0.66
    (!__
    -0.66
    ########.
    -0.66
    Tikang
    -0.65
    ',
    -0.65
    POSITIVE LOGITS
     algún
    0.44
     alguna
    0.44
     alguno
    0.39
     fidèles
    0.38
     kiedyś
    0.38
    .
    0.37
     eventually
    0.37
     algum
    0.36
     nantinya
    0.36
     irgendwann
    0.35
    Act Density 0.003%

    No Known Activations