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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration or value for concepts and ideas

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

    metaphors and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蚪
    -0.40
     rutin
    -0.39
     Corsa
    -0.37
     NgModule
    -0.36
    msgTypes
    -0.35
    NgModule
    -0.34
     fusil
    -0.33
     linkovi
    -0.33
    PMailer
    -0.33
     confiance
    -0.33
    POSITIVE LOGITS
    ftagPool
    0.51
     poetic
    0.51
     coined
    0.50
     reson
    0.48
    criptors
    0.47
     quote
    0.47
    enderror
    0.47
     resonate
    0.47
     begre
    0.47
     придума
    0.46
    Act Density 0.047%

    No Known Activations