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

    Neuronpedia

    INDEX
    Explanations

    sequences of numeric values or identifiers

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istoitu
    -0.69
     cherchés
    -0.61
    httphttps
    -0.60
    脚注の使い方
    -0.58
    MemoryWarning
    -0.57
    ArrowToggle
    -0.57
    Παραπομπές
    -0.57
     المعيارى
    -0.56
     Meksiku
    -0.56
    ftagPool
    -0.51
    POSITIVE LOGITS
     arrow
    0.40
     Sam
    0.37
     inf
    0.37
     State
    0.37
     Ryan
    0.36
     Riz
    0.34
     Riley
    0.34
     Ay
    0.34
    ритори
    0.34
     Sams
    0.33
    Act Density 0.018%

    No Known Activations