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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ining
    -0.07
    Trim
    -0.07
    aning
    -0.06
     jag
    -0.06
    manage
    -0.06
     Avust
    -0.06
     dgv
    -0.06
    -Mail
    -0.06
     tjejer
    -0.06
     bean
    -0.06
    POSITIVE LOGITS
    Say
    0.09
     đến
    0.07
    →
    0.07
     SQ
    0.07
     до
    0.07
     возникает
    0.07
     tới
    0.07
    鼻
    0.07
    :
    0.07
     次
    0.07
    Act Density 0.026%

    No Known Activations