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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thresh
    -0.07
    iola
    -0.07
     cerebral
    -0.07
    第七
    -0.07
    justice
    -0.07
     Jeh
    -0.07
     caz
    -0.07
    Matthew
    -0.07
     StreamWriter
    -0.07
     Annie
    -0.07
    POSITIVE LOGITS
    _g
    0.07
     ")";↵
    0.06
    ...");↵
    0.06
    opleft
    0.06
     ">↵
    0.06
    {s
    0.06
    '");↵
    0.06
    ﻋ
    0.06
    Italian
    0.06
    跟踪
    0.06
    Act Density 0.001%

    No Known Activations