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

    Neuronpedia

    INDEX
    Explanations

    terms related to enabling and disabling features or settings

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

    Enabling or disabling features

    np_acts-logits-general · gemini-2.0-flash

    enable or disable features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     religieuses
    -0.67
     sorte
    -0.65
    rungsseite
    -0.64
     asiatique
    -0.64
    verwijspagina
    -0.63
     devoir
    -0.63
     abstrait
    -0.63
    ItemBackground
    -0.63
     générale
    -0.61
    writeFieldEnd
    -0.60
    POSITIVE LOGITS
    ../../
    0.71
    inguez
    0.71
    ../
    0.68
    netics
    0.67
    ized
    0.62
    onsored
    0.61
    urator
    0.60
    )="
    0.60
    izing
    0.60
     paraly
    0.59
    Act Density 0.161%

    No Known Activations