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

    Neuronpedia

    INDEX
    Explanations

    image alt attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dependences
    0.46
     horrible
    0.43
     horrifying
    0.42
     treason
    0.41
     requer
    0.40
     assh
    0.40
     awful
    0.40
     creepy
    0.40
    ំន
    0.40
     willst
    0.40
    POSITIVE LOGITS
     Ubuy
    0.49
    𝐟
    0.46
    售价
    0.46
     Canva
    0.46
    🥹
    0.46
    抖音
    0.44
    ᐈ
    0.43
    🤎
    0.43
    🥰
    0.42
    🫶
    0.42
    Act Density 0.001%

    No Known Activations