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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reverted
    -0.07
     Tah
    -0.06
     UIT
    -0.06
    (play
    -0.06
     illicit
    -0.06
     Ath
    -0.06
     至
    -0.06
    poz
    -0.06
     bosses
    -0.06
    ją
    -0.06
    POSITIVE LOGITS
    	finally
    0.07
    URRENT
    0.06
    553
    0.06
    iman
    0.06
     Eston
    0.06
    grounds
    0.06
    迎
    0.06
    edelta
    0.06
    	intent
    0.06
    keeper
    0.06
    Act Density 0.033%

    No Known Activations