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

    Neuronpedia

    INDEX
    Explanations

    terms related to scoring leads and advantages in competitive games

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

    leading in competitive contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     girasol
    -0.40
     veau
    -0.39
     portes
    -0.38
     Calidad
    -0.38
     gré
    -0.37
     remark
    -0.35
     thrift
    -0.35
    throwable
    -0.35
     marketplace
    -0.35
    elemField
    -0.35
    POSITIVE LOGITS
     nahilalakip
    0.61
    ConstraintMaker
    0.60
     محفوظة
    0.57
    possession
    0.54
    disposing
    0.53
    addCriterion
    0.52
    GEBURTSDATUM
    0.52
    SequentialGroup
    0.51
     Possession
    0.50
    DockStyle
    0.50
    Act Density 0.015%

    No Known Activations