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

    Neuronpedia

    INDEX
    Explanations

    numbers and their contextual significance or calculations

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

    numbers starting with 76

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.48
     препратки
    -0.45
    needs
    -0.44
    Pautan
    -0.42
    dir
    -0.41
     Clow
    -0.40
     kaarangay
    -0.40
    ɲ
    -0.40
    بوابة
    -0.40
    ophor
    -0.39
    POSITIVE LOGITS
     userType
    0.60
    mpe
    0.57
     ſte
    0.57
     navideñas
    0.53
    userType
    0.53
     getUsername
    0.52
     Wilk
    0.52
     amarillas
    0.52
    userRepository
    0.51
     ſche
    0.51
    Act Density 0.129%

    No Known Activations