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

    Neuronpedia

    INDEX
    Explanations

    words related to moral and ethical values

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

    values and beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.46
     виправивши
    -0.43
    WidgetItem
    -0.43
     }{@
    -0.42
    pero
    -0.42
    HttpPut
    -0.41
    <bos>
    -0.39
    GraphicsUnit
    -0.38
    ValueStyle
    -0.38
    }}}}
    -0.38
    POSITIVE LOGITS
    estacks
    0.57
     ​​
    0.54
     BorderRadius
    0.48
    évaluateur
    0.44
    brtc
    0.43
     instilled
    0.43
     fondament
    0.42
     AssemblyCulture
    0.40
    lapsingToolbar
    0.39
     orientation
    0.39
    Act Density 0.011%

    No Known Activations