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

    Neuronpedia

    INDEX
    Explanations

    questions and concerns regarding instructions, processes, or decision-making

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

    explaining contextually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.74
     الرياضيه
    -0.66
    __':
    -0.66
    PerformLayout
    -0.61
     Мексичка
    -0.56
     виправивши
    -0.54
    رشف
    -0.53
     Italijanski
    -0.52
     TAMBIÉN
    -0.52
     noDo
    -0.51
    POSITIVE LOGITS
    l
    0.39
     crystal
    0.36
    cal
    0.35
     Fe
    0.35
     intelligent
    0.34
    cons
    0.34
    h
    0.34
     validamos
    0.32
    ins
    0.32
     Ray
    0.32
    Act Density 0.116%

    No Known Activations