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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    share
    -0.06
     mex
    -0.06
     patiently
    -0.06
     bitten
    -0.06
    notify
    -0.06
     watched
    -0.06
    ạm
    -0.06
     watch
    -0.06
     궁금
    -0.06
    vida
    -0.06
    POSITIVE LOGITS
     �
    0.08
     =
    0.08
    ='
    0.07
     gió
    0.07
    ΟΥ
    0.07
    ="
    0.07
     predomin
    0.07
    ;(
    0.07
    .isNotEmpty
    0.07
    =
    0.06
    Act Density 0.025%

    No Known Activations