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

    Neuronpedia

    INDEX
    Explanations

    specific phonetic patterns, particularly those resembling syllables or prefixes in words

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

    gulpahum, Zalman call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ApiRequest
    -0.57
    setContentView
    -0.54
    CppMethod
    -0.52
    getSystem
    -0.49
    googleapis
    -0.48
    ReactDOM
    -0.46
     Wiktionnaire
    -0.46
     Krä
    -0.45
    ioso
    -0.45
    /*++
    -0.45
    POSITIVE LOGITS
    alpa
    0.55
    Elsa
    0.53
    elm
    0.53
     Elmo
    0.53
     Elsa
    0.53
    ALM
    0.49
     alm
    0.49
     Aldi
    0.47
     alt
    0.46
     ALC
    0.46
    Act Density 0.063%

    No Known Activations