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

    Neuronpedia

    INDEX
    Explanations

    various

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Km
    -0.07
     JJ
    -0.07
    _Global
    -0.07
     startX
    -0.06
     Gil
    -0.06
    310
    -0.06
    年に
    -0.06
     anale
    -0.06
    :YES
    -0.06
     kcal
    -0.06
    POSITIVE LOGITS
     педагог
    0.07
     cảnh
    0.06
     bóng
    0.06
     erhalten
    0.06
     nou
    0.06
    角色
    0.06
    êt
    0.06
    ОР
    0.06
     Surprise
    0.05
     اسر
    0.05
    Act Density 0.120%

    No Known Activations