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

    Neuronpedia

    INDEX
    Explanations

    computer code and programs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )
    -0.08
     INCIDENTAL
    -0.07
     explicit
    -0.07
    ()
    -0.07
    かつ
    -0.07
     })↵↵
    -0.07
    Electronic
    -0.06
    ประจำ
    -0.06
    마다
    -0.06
    以便
    -0.06
    POSITIVE LOGITS
    ROOM
    0.08
    舟山
    0.07
     Zimmer
    0.07
     סרט
    0.07
    users
    0.07
     fishes
    0.06
     fiery
    0.06
    _unknown
    0.06
     gre
    0.06
    朗诵
    0.06
    Act Density 0.000%

    No Known Activations