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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stressed
    -0.08
     BusinessException
    -0.08
     موا
    -0.07
     Ply
    -0.07
    DatePicker
    -0.07
     Colts
    -0.07
     fps
    -0.07
    ѳ
    -0.07
    鸱
    -0.07
     compl
    -0.07
    POSITIVE LOGITS
    ::::::::
    0.08
     ```↵
    0.08
        ↵
    0.08
     Lounge
    0.07
    }*/↵
    0.07
    amo
    0.07
    薯
    0.07
            ↵
    0.07
    🦑
    0.07
    חות
    0.07
    Act Density 0.004%

    No Known Activations