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
     argue
    -0.07
    les
    -0.07
    lisi
    -0.06
     dados
    -0.06
     PASS
    -0.06
    /blog
    -0.06
    _ENT
    -0.06
     inconsistent
    -0.06
     Eagles
    -0.06
    oy
    -0.06
    POSITIVE LOGITS
     своим
    0.07
     torchvision
    0.06
     defiance
    0.06
     индивиду
    0.06
     víde
    0.06
     treasury
    0.06
    flen
    0.06
     그를
    0.06
     te
    0.06
     dalších
    0.06
    Act Density 0.002%

    No Known Activations