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
    laps
    -0.07
     nosso
    -0.07
     Kra
    -0.06
    mediately
    -0.06
     вся
    -0.06
    们
    -0.06
    liğinin
    -0.06
     '#{
    -0.06
    審
    -0.06
    Defs
    -0.06
    POSITIVE LOGITS
    uffed
    0.07
     Zo
    0.07
     ки
    0.07
    /',↵
    0.06
     Moon
    0.06
    Moon
    0.06
     Christopher
    0.06
     ***↵
    0.06
     Jade
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations