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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "ang" and its associations

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

    Xang words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ')))
    -0.50
    ···
    -0.50
    •••
    -0.49
    ••
    -0.48
    })-\
    -0.45
    }))
    -0.44
    )"),
    -0.43
    ⑦
    -0.42
    }}},
    -0.42
    SuppressLint
    -0.42
    POSITIVE LOGITS
    ang
    1.05
    ANG
    0.96
     Zang
    0.82
    anger
    0.80
     ANG
    0.79
    Jang
    0.77
     Mang
    0.75
    arang
    0.74
    Mang
    0.74
    angling
    0.74
    Act Density 0.034%

    No Known Activations