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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to chemical reactions and their potential dangers

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

    danger and hazards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cómoda
    -0.33
     Entscheidung
    -0.31
     brindar
    -0.29
    itoare
    -0.27
     masalah
    -0.27
     Entscheidungen
    -0.27
     problèmes
    -0.27
     ruidos
    -0.27
     oluyor
    -0.27
     skj
    -0.25
    POSITIVE LOGITS
     ſever
    0.69
    AutoScaleMode
    0.68
    CloseOperation
    0.65
     незавершена
    0.64
    PerformLayout
    0.62
    StructEnd
    0.62
     cauſe
    0.60
    存于互联网档案馆
    0.60
    ſelf
    0.59
     ſta
    0.59
    Act Density 0.032%

    No Known Activations