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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \xaa
    -0.07
     topp
    -0.07
    ])]↵
    -0.07
    罂
    -0.07
    征
    -0.07
    veau
    -0.07
    -ce
    -0.07
    xo
    -0.07
     bursts
    -0.06
    党总
    -0.06
    POSITIVE LOGITS
    갚
    0.07
    上下游
    0.07
    耕地
    0.07
    Nib
    0.07
    Attachment
    0.07
    Particle
    0.06
    _dr
    0.06
    Mix
    0.06
    нер
    0.06
     Minneapolis
    0.06
    Act Density 0.021%

    No Known Activations