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

    Neuronpedia

    INDEX
    Explanations

    phrases reflecting the complexity of choice and responsibility in human actions

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

    even, when, or whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.63
    IBarButtonItem
    -0.60
     Normdatei
    -0.60
    ########.
    -0.57
     invokingState
    -0.56
    RepeatedField
    -0.53
     OnTriggerEnter
    -0.52
     ChromeDriver
    -0.51
    MLLoader
    -0.51
    matchCondition
    -0.50
    POSITIVE LOGITS
    zeiger
    0.39
    FromArgb
    0.37
    jmniej
    0.36
    Даже
    0.35
     GLASS
    0.35
     wenigstens
    0.33
     querr
    0.33
    Glass
    0.33
    oarece
    0.33
     Glass
    0.32
    Act Density 0.032%

    No Known Activations