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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms associated with performances, success, and applause

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

    performance, encore, triumph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebControls
    -0.45
    ViewImports
    -0.36
    setObjectName
    -0.33
     pyplot
    -0.33
    awaiter
    -0.32
     guida
    -0.31
    Itoa
    -0.31
    thulhu
    -0.31
    IntoConstraints
    -0.31
    poz
    -0.30
    POSITIVE LOGITS
     الرياضيه
    0.68
     ovation
    0.61
     Encore
    0.57
    Encore
    0.54
    OOTDTY
    0.52
    lause
    0.50
     Publikum
    0.50
     Italijanski
    0.50
    ckså
    0.50
     triump
    0.49
    Act Density 0.057%

    No Known Activations