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

    Neuronpedia

    INDEX
    Explanations

    CSS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rue
    -0.06
    adows
    -0.06
     Leak
    -0.06
     ICU
    -0.06
    ôn
    -0.06
     Specialists
    -0.06
    *K
    -0.06
     SS
    -0.06
     AES
    -0.06
    IID
    -0.06
    POSITIVE LOGITS
    _MULTI
    0.07
     freight
    0.07
    َع
    0.07
    (point
    0.07
    .We
    0.06
     governors
    0.06
     exhilar
    0.06
    Opp
    0.06
     Tin
    0.06
    왕
    0.06
    Act Density 0.003%

    No Known Activations