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

    Neuronpedia

    INDEX
    Explanations

    instances of replacement or substitution in mathematical expressions

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

    replace with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    معلومات
    -0.34
    unnitel
    -0.31
     Brunnen
    -0.31
    HXLINE
    -0.30
     Werk
    -0.30
    เก
    -0.29
    Demografía
    -0.29
     comigo
    -0.28
     Kelurahan
    -0.28
     оригіналу
    -0.28
    POSITIVE LOGITS
    adaptiveStyles
    0.69
    RegressionTest
    0.55
    EndContext
    0.53
    Captor
    0.53
    oa̍t
    0.52
    ResponseWriter
    0.52
     betweenstory
    0.51
    MemoryWarning
    0.49
     Cone
    0.48
    +:+
    0.48
    Act Density 0.608%

    No Known Activations