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

    Neuronpedia

    INDEX
    Explanations

    terms related to continuity and unobstructed conditions

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

    without interruption or disturbance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.53
    expandindo
    -0.52
    istoitu
    -0.50
     falschen
    -0.49
    Kanpo
    -0.49
    tableFuture
    -0.46
    Worse
    -0.46
    stupid
    -0.45
     ferons
    -0.45
    wrong
    -0.44
    POSITIVE LOGITS
     uninterrupted
    1.63
     undisturbed
    1.26
     unbroken
    1.23
     unim
    1.09
     unob
    1.01
     unrestricted
    0.95
     unaffected
    0.85
     unab
    0.79
     undisputed
    0.77
     uncomplicated
    0.76
    Act Density 0.019%

    No Known Activations