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

    Neuronpedia

    INDEX
    Explanations

    Code and Japanese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ాయం
    -0.09
     freien
    -0.09
    қ
    -0.08
     Write
    -0.08
     repreh
    -0.08
    ാത
    -0.08
     الحرة
    -0.08
     Mm
    -0.08
     Twist
    -0.08
    ategorien
    -0.08
    POSITIVE LOGITS
     corporal
    0.07
     મુક
    0.07
    160
    0.07
     দু
    0.07
     occurrences
    0.07
     stuff
    0.07
     instances
    0.07
     sandy
    0.07
     marketing
    0.07
    019
    0.07
    Act Density 0.000%

    No Known Activations