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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal opinions and recommendations

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

    Talking or objecting

    np_acts-logits-general · gemini-2.0-flash

    talking about things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.78
    IUrlHelper
    -0.72
     AssemblyCulture
    -0.61
    acherous
    -0.61
    hyo
    -0.59
     diputados
    -0.58
    SourceChecksum
    -0.58
     Wikimedijinoj
    -0.58
    няття
    -0.55
     segnale
    -0.55
    POSITIVE LOGITS
     rambling
    1.11
     anecdotes
    0.96
    滔
    0.94
     tangents
    0.91
     rant
    0.87
     ranting
    0.83
     philosophi
    0.82
     reminis
    0.79
     chit
    0.78
     topics
    0.78
    Act Density 0.413%

    No Known Activations