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

    Neuronpedia

    INDEX
    Explanations

    patterns of dashes and underscores that may represent sections or divisions in a structured format

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

    documentation and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.49
    DIPSETTING
    -0.48
    Rhestr
    -0.47
    TagMode
    -0.47
     esternos
    -0.47
    ChromeDriver
    -0.46
    verifyException
    -0.46
     Infórmanos
    -0.46
    Datuak
    -0.46
     Italijani
    -0.45
    POSITIVE LOGITS
    ItemLayout
    0.40
    protoimpl
    0.37
     Muda
    0.37
    bibfield
    0.36
     Fighters
    0.36
    Serializable
    0.36
    arsa
    0.36
    IntoConstraints
    0.36
    ίναι
    0.36
     defaultstate
    0.35
    Act Density 0.112%

    No Known Activations