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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toen
    -0.07
     actionPerformed
    -0.07
     kötü
    -0.07
     burn
    -0.07
    /loader
    -0.07
     Randall
    -0.06
    vrd
    -0.06
    เตร
    -0.06
    uda
    -0.06
     rdr
    -0.06
    POSITIVE LOGITS
    6
    0.14
    06
    0.08
    4
    0.08
    9
    0.07
    0
    0.07
    7
    0.07
    12
    0.07
    ۶
    0.07
    १
    0.07
    ิการ
    0.07
    Act Density 0.127%

    No Known Activations