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

    Neuronpedia

    INDEX
    Explanations

    _param

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enes
    -0.07
     tp
    -0.06
    $conn
    -0.06
     존
    -0.06
     зобов
    -0.06
    _mag
    -0.06
    dep
    -0.06
     robes
    -0.06
     λι
    -0.06
    $app
    -0.06
    POSITIVE LOGITS
     Bran
    0.07
    amaha
    0.07
     cod
    0.07
     workaround
    0.07
    SPORT
    0.06
    افع
    0.06
    uv
    0.06
     Gdk
    0.06
     squid
    0.06
     Prepare
    0.06
    Act Density 0.002%

    No Known Activations