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

    Neuronpedia

    INDEX
    Explanations

    messages related to debugging and error reporting

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

    Code, debugging, or math-related text

    np_acts-logits-general · gemini-2.0-flash

    lookup keyboard | mass experiments | Respiratory syncytial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.74
    %");
    -0.71
     виправивши
    -0.71
    '){
    -0.71
    ^(@)
    -0.70
    $.
    -0.69
    .";
    -0.68
     ?',
    -0.68
     تكبرها
    -0.66
    \{\\
    -0.66
    POSITIVE LOGITS
    :
    0.82
    :"
    0.64
    !
    0.64
    :\
    0.63
    ",
    0.61
     got
    0.59
    !!!
    0.59
    !!!!
    0.58
     =>
    0.58
     -
    0.57
    Act Density 0.272%

    No Known Activations