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

    Neuronpedia

    INDEX
    Explanations

    Succubi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     застав
    -0.07
     UNITY
    -0.07
     Apparently
    -0.07
     ninth
    -0.06
     Prel
    -0.06
     prevail
    -0.06
     demonstrated
    -0.06
     maximize
    -0.06
    Overall
    -0.06
    Apparently
    -0.06
    POSITIVE LOGITS
    accounts
    0.07
    ピ
    0.06
     Fix
    0.06
    月
    0.06
    ポイント
    0.06
    _sms
    0.06
    wives
    0.06
    
↵
    0.06
    work
    0.06
     О
    0.06
    Act Density 0.001%

    No Known Activations