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

    Neuronpedia

    INDEX
    Explanations

    production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marketed
    -0.06
     Personal
    -0.06
    cam
    -0.06
    Entre
    -0.06
    duce
    -0.06
    _Rem
    -0.06
     ymin
    -0.05
    _GEN
    -0.05
     aprox
    -0.05
    	wait
    -0.05
    POSITIVE LOGITS
    컵
    0.07
     LES
    0.07
    튜
    0.06
     Bean
    0.06
     kategor
    0.06
    ोज
    0.06
     knull
    0.06
     Počet
    0.06
    =tk
    0.06
     textu
    0.06
    Act Density 0.021%

    No Known Activations