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

    Neuronpedia

    INDEX
    Explanations

    say rgba

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    威廉
    -0.07
     Jerry
    -0.07
     (($
    -0.07
     mâ
    -0.07
     struggling
    -0.07
    俄罗斯
    -0.07
     brigade
    -0.07
     Velvet
    -0.07
     bab
    -0.07
     chac
    -0.06
    POSITIVE LOGITS
    /alert
    0.07
    _sim
    0.07
    METHOD
    0.07
    .l
    0.07
    少见
    0.07
    (layout
    0.06
    .core
    0.06
     biom
    0.06
    atal
    0.06
    قات
    0.06
    Act Density 0.000%

    No Known Activations