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

    Neuronpedia

    INDEX
    Explanations

    conditional statements related to potential issues or risks

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

    conditional explanations in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Decke
    -0.43
     camiset
    -0.41
     detik
    -0.40
     tamam
    -0.40
     brilhante
    -0.39
     bēr
    -0.39
    èbre
    -0.38
     lojas
    -0.38
    sstelle
    -0.37
    Instantiation
    -0.37
    POSITIVE LOGITS
    AddTagHelper
    0.71
    httphttps
    0.67
    GEBURTSDATUM
    0.63
     cherchés
    0.63
    Sucesor
    0.54
    endpush
    0.51
    endphp
    0.51
     Infórmanos
    0.50
     */
    0.50
    inSlope
    0.50
    Act Density 0.006%

    No Known Activations