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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     técnico
    -0.07
     ceil
    -0.07
     fem
    -0.07
     bueno
    -0.07
    에너
    -0.07
    渗透
    -0.06
    .dropdown
    -0.06
    Merc
    -0.06
     determin
    -0.06
     Sem
    -0.06
    POSITIVE LOGITS
    屡
    0.07
    ]$
    0.07
    獎
    0.07
    怀疑
    0.07
    制
    0.07
     계속
    0.07
    (xpath
    0.07
    дает
    0.07
    string
    0.07
    ール
    0.07
    Act Density 0.015%

    No Known Activations