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

    Neuronpedia

    INDEX
    Explanations

    in section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ickey
    -0.07
    ﮃ
    -0.07
     rookies
    -0.07
    เทค
    -0.06
     Hidden
    -0.06
    dock
    -0.06
    Decision
    -0.06
    舄
    -0.06
    ᐃ
    -0.06
     Name
    -0.06
    POSITIVE LOGITS
     גיל
    0.07
    +W
    0.07
    ête
    0.07
     покупа
    0.07
    .el
    0.06
     "^
    0.06
    _g
    0.06
     أيضا
    0.06
    _ACK
    0.06
     לחלוטין
    0.06
    Act Density 0.007%

    No Known Activations