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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reduce
    -0.07
     don
    -0.07
     Total
    -0.07
     We
    -0.06
    We
    -0.06
    .We
    -0.06
     FTP
    -0.06
     :::
    -0.06
    イント
    -0.06
     decreasing
    -0.06
    POSITIVE LOGITS
    RY
    0.09
     máy
    0.07
    Alexander
    0.07
    ๋
    0.07
    rys
    0.07
    нина
    0.07
     Alexander
    0.06
    ина
    0.06
     the
    0.06
    amil
    0.06
    Act Density 0.764%

    No Known Activations