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

    Neuronpedia

    INDEX
    Explanations

    individually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wen
    -0.08
     देख
    -0.08
     fring
    -0.08
     factions
    -0.07
     ची
    -0.07
     toxic
    -0.07
     tastes
    -0.07
     Proceed
    -0.07
     frig
    -0.07
     nobody
    -0.07
    POSITIVE LOGITS
     Leop
    0.10
     Bonn
    0.09
    నే
    0.08
     Θε
    0.08
     separately
    0.08
    hil
    0.08
    -अलग
    0.08
    ியே
    0.08
     পৃথ
    0.08
     والاج
    0.08
    Act Density 0.007%

    No Known Activations