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

    Neuronpedia

    INDEX
    Explanations

    code snippets or structures indicating closing braces and conditional logic in programming

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

    end of code block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.46
    Ҭ
    -0.44
    IntoConstraints
    -0.44
    GOTREF
    -0.44
     الحره
    -0.43
     gyhoeddwyd
    -0.43
    الدراسه
    -0.42
    MLLoader
    -0.38
     IBOutlet
    -0.37
    fxml
    -0.36
    POSITIVE LOGITS
    Bibliograf
    0.52
    Enllaces
    0.49
     novio
    0.46
    Aholisi
    0.45
     HFILL
    0.43
     uitzicht
    0.42
     novia
    0.42
    ẨM
    0.41
    noopener
    0.41
     novios
    0.41
    Act Density 0.013%

    No Known Activations