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

    Neuronpedia

    INDEX
    Explanations

    references to hosting and events

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

    hosting websites or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.38
    はじめに
    -0.35
    fillType
    -0.31
    Delimited
    -0.31
    RTSC
    -0.31
    ----</
    -0.30
     pows
    -0.29
     práctica
    -0.29
    <?
    -0.28
    InstrumentedTest
    -0.28
    POSITIVE LOGITS
     host
    1.61
     Host
    1.55
     hosts
    1.49
    Host
    1.41
     Hosts
    1.40
     hosting
    1.37
     HOST
    1.36
    host
    1.31
     hosted
    1.29
     Hosting
    1.24
    Act Density 0.036%

    No Known Activations