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

    Neuronpedia

    INDEX
    Explanations

    words related to new additions or enhancements to various contexts

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

    addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gastroenter
    -0.54
    mycompany
    -0.53
    userProfile
    -0.52
    caneca
    -0.51
    yticks
    -0.49
    cartera
    -0.48
    PRACT
    -0.48
    ansky
    -0.47
    coffret
    -0.47
    painel
    -0.47
    POSITIVE LOGITS
     addition
    1.95
     Addition
    1.76
    addition
    1.74
    Addition
    1.70
     additions
    1.63
     Additions
    1.42
    Additions
    1.28
     доба
    1.01
     추가
    0.93
     addi
    0.93
    Act Density 0.018%

    No Known Activations