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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LAW
    -0.07
    ètre
    -0.06
     Серед
    -0.06
    инг
    -0.06
     fet
    -0.06
    (ap
    -0.06
     evaluated
    -0.06
     καλύ
    -0.06
    �
    -0.06
    นาน
    -0.06
    POSITIVE LOGITS
    인
    0.07
     회사
    0.06
    abra
    0.06
    erokee
    0.06
     extra
    0.06
    ').'</
    0.06
    Mirror
    0.06
     fairly
    0.06
     road
    0.06
     строитель
    0.06
    Act Density 0.002%

    No Known Activations