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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    querque
    -0.07
    _addr
    -0.06
    nThe
    -0.06
     Κά
    -0.06
    	not
    -0.06
    strtotime
    -0.06
    alyzer
    -0.06
    .Trans
    -0.06
     služ
    -0.06
    二二
    -0.06
    POSITIVE LOGITS
    0.07
     priority
    0.07
    0.07
     LOVE
    0.06
    iard
    0.06
    0.06
    0.06
     tendencies
    0.06
    ุ้
    0.06
    ох
    0.06
    Act Density 0.002%

    No Known Activations