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

    Neuronpedia

    INDEX
    Explanations

    Code and programming text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cann
    -0.07
     Nan
    -0.07
    -ring
    -0.07
     Norte
    -0.07
    tablet
    -0.07
     Elite
    -0.06
     Num
    -0.06
     Worlds
    -0.06
     Pin
    -0.06
     linh
    -0.06
    POSITIVE LOGITS
    redit
    0.07
     Quite
    0.07
     rested
    0.07
     clumsy
    0.06
    'action
    0.06
     постро
    0.06
    737
    0.06
    chosen
    0.06
    bugs
    0.06
     missed
    0.06
    Act Density 0.052%

    No Known Activations