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

    Neuronpedia

    INDEX
    Explanations

    __

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raging
    -0.08
    青年
    -0.08
    AVED
    -0.07
     lớn
    -0.07
     avg
    -0.06
    ík
    -0.06
    몰
    -0.06
     الهند
    -0.06
    itta
    -0.06
     populous
    -0.06
    POSITIVE LOGITS
     beads
    0.06
     Threads
    0.06
    iode
    0.06
    icopt
    0.06
    _SPR
    0.06
    interested
    0.06
     {}).
    0.06
    /User
    0.06
     Cannot
    0.06
    @Injectable
    0.06
    Act Density 0.001%

    No Known Activations