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

    Neuronpedia

    INDEX
    Explanations

    terms related to constraints and allowed operations in mathematical contexts

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

    restrictions and allowances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niająca
    -0.45
     médaille
    -0.39
    jsonwebtoken
    -0.38
     Италијани
    -0.37
    Diwedd
    -0.36
    needed
    -0.36
     perfe
    -0.36
     needful
    -0.36
    Triumph
    -0.36
     Económica
    -0.36
    POSITIVE LOGITS
    inSlope
    0.51
     constraints
    0.50
     restricted
    0.44
     restrictions
    0.44
     RESTRICT
    0.43
     constraint
    0.42
     ограничения
    0.41
     limited
    0.41
     запре
    0.40
     restriction
    0.40
    Act Density 0.165%

    No Known Activations