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

    Neuronpedia

    INDEX
    Explanations

    logs/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vat
    -0.07
    rex
    -0.07
    iga
    -0.06
     мог
    -0.06
    жен
    -0.06
     belt
    -0.06
    肌
    -0.06
     isp
    -0.06
     dün
    -0.06
     був
    -0.06
    POSITIVE LOGITS
    _MPI
    0.07
    \",\
    0.07
     utiliz
    0.07
    .randomUUID
    0.06
     ventil
    0.06
     groundwork
    0.06
     +
    0.06
    ")+
    0.06
    ]}
    0.06
     Norwich
    0.06
    Act Density 0.001%

    No Known Activations