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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    떄
    -0.07
    /example
    -0.07
     connection
    -0.06
    diğim
    -0.06
    我不是
    -0.06
     Modified
    -0.06
    בדק
    -0.06
    ировал
    -0.06
     أصبح
    -0.06
     freder
    -0.06
    POSITIVE LOGITS
    _traj
    0.08
    opause
    0.08
    比例
    0.07
     axe
    0.07
    ate
    0.07
     regime
    0.07
     =>
↵
    0.07
    _abort
    0.07
    ἁ
    0.07
    دة
    0.07
    Act Density 0.014%

    No Known Activations