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

    Neuronpedia

    INDEX
    Explanations

    turns of phrase that indicate a break or transition in a conversation

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

    foreign language words and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    errHandler
    -0.45
    jspx
    -0.43
     otomatig
    -0.42
    IntoConstraints
    -0.39
     Jeffrey
    -0.38
    enumi
    -0.38
    protoimpl
    -0.38
    zzlement
    -0.38
    AndEndTag
    -0.37
     }{@
    -0.37
    POSITIVE LOGITS
     teck
    0.48
     nonUne
    0.46
     étoient
    0.45
     enfans
    0.42
    ﹠
    0.41
    "$_
    0.39
    zeptember
    0.38
     Италијани
    0.38
    =$?
    0.37
    Heim
    0.36
    Act Density 0.531%

    No Known Activations