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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    REQUIRED
    -0.07
     Partition
    -0.07
    _req
    -0.07
    -prof
    -0.07
     userManager
    -0.07
    _ORDER
    -0.07
    _Item
    -0.06
     rooft
    -0.06
     horas
    -0.06
     late
    -0.06
    POSITIVE LOGITS
     mohli
    0.07
    nutí
    0.06
    ched
    0.06
    '));
↵
    0.06
     浙江
    0.06
     resultat
    0.06
     орган
    0.06
    Kelly
    0.06
    Sk
    0.06
    ，加
    0.06
    Act Density 0.025%

    No Known Activations