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

    Neuronpedia

    INDEX
    Explanations

    the presence of essential headers or commands in code-like structures

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

    Questions/answers or code snippets

    np_acts-logits-general · gemini-2.0-flash

    question-answer structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wtf
    -0.65
    ]+$
    -0.62
    WriteTagHelper
    -0.61
     незавершена
    -0.59
    wtf
    -0.59
     imo
    -0.55
     transfieras
    -0.53
     WTF
    -0.53
    ølge
    -0.52
    <?>
    -0.52
    POSITIVE LOGITS
     nakalista
    0.79
     tonight
    0.71
    刚才
    0.69
    parsedMessage
    0.68
     Tonight
    0.66
     momentarily
    0.65
     Joining
    0.65
     unmute
    0.63
     applau
    0.62
    Joining
    0.62
    Act Density 0.113%

    No Known Activations