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
     vlastně
    -0.08
           
↵
    -0.08
    لح
    -0.07
    われ
    -0.06
     communal
    -0.06
    wdx
    -0.06
    。不
    -0.06
    修
    -0.06
    /Internal
    -0.06
     zm
    -0.06
    POSITIVE LOGITS
    >:
    0.06
     sophistication
    0.06
    %!
    0.06
     extinction
    0.06
     rabbits
    0.06
    -goal
    0.06
    INO
    0.06
    adol
    0.06
     inhibition
    0.06
    ida
    0.06
    Act Density 0.000%

    No Known Activations