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

    Neuronpedia

    INDEX
    Explanations

    phrases related to terms and conditions or restrictions in an agreement

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

    catch or qualify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guided
    -0.47
    guided
    -0.40
    newName
    -0.38
    bide
    -0.38
    ynomial
    -0.38
    érêt
    -0.37
     ungu
    -0.37
    sibirsk
    -0.37
     Bourg
    -0.36
    closedir
    -0.36
    POSITIVE LOGITS
     arşivlendi
    0.52
    +#+#
    0.47
     restrictions
    0.46
    ApiModelProperty
    0.46
    ConstraintMaker
    0.45
    styleable
    0.44
    RegressionTest
    0.41
     Restrictions
    0.41
     iconTwitter
    0.41
     الحره
    0.41
    Act Density 0.020%

    No Known Activations