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

    Neuronpedia

    INDEX
    Explanations

    specific brand names and notable products in various contexts

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

    Liberty Style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.45
    complexType
    -0.42
    Vidite
    -0.40
    ghold
    -0.39
     hyvin
    -0.35
    ceğine
    -0.34
     hỏi
    -0.34
     récemment
    -0.33
    躇
    -0.33
    demi
    -0.33
    POSITIVE LOGITS
    StructEnd
    0.57
     demografica
    0.57
     popping
    0.53
     Normdatei
    0.52
     strangled
    0.44
    ⁝
    0.44
     الرياضيه
    0.43
     pop
    0.43
     CreateTagHelper
    0.43
    …~
    0.43
    Act Density 0.033%

    No Known Activations