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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and critiques of behavior or societal norms

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

    pretends that, utilize in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lank
    -0.37
    SceneManagement
    -0.37
     HomeScreen
    -0.35
     durian
    -0.34
     inder
    -0.33
     Ichigo
    -0.33
    COE
    -0.33
    Stor
    -0.33
     OkHttpClient
    -0.32
    ğ
    -0.32
    POSITIVE LOGITS
    Билгалдахарш
    0.77
     femininos
    0.60
     définiti
    0.53
     públicos
    0.50
     říká
    0.50
     femininas
    0.48
     referenties
    0.47
    ftagPool
    0.47
     czego
    0.46
    httphttps
    0.46
    Act Density 0.062%

    No Known Activations