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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     probí
    -0.07
     Brend
    -0.07
     اثر
    -0.07
     accountable
    -0.06
     Designs
    -0.06
     STOP
    -0.06
     Found
    -0.06
     Sel
    -0.06
     Hole
    -0.06
     хозяй
    -0.06
    POSITIVE LOGITS
    ------↵↵
    0.07
    isdigit
    0.07
                                 ↵
    0.07
                       ↵
    0.06
    FH
    0.06
     UIImage
    0.06
    .environ
    0.06
                      ↵
    0.06
     कहत
    0.06
    .documentation
    0.06
    Act Density 0.017%

    No Known Activations