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

    Neuronpedia

    INDEX
    Explanations

    Plans and strategy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Job
    -0.07
    暂
    -0.07
     xu
    -0.07
     яв
    -0.07
     VIC
    -0.07
     vừa
    -0.07
    吴
    -0.06
     lifted
    -0.06
     offences
    -0.06
     supers
    -0.06
    POSITIVE LOGITS
    Inflater
    0.08
     Begins
    0.07
    (enemy
    0.07
    カラー
    0.07
    اعتم
    0.07
    ~-~-~-~-
    0.07
    Cached
    0.07
     IllegalStateException
    0.07
     Learned
    0.06
     reli
    0.06
    Act Density 0.128%

    No Known Activations