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

    Neuronpedia

    INDEX
    Explanations

    priority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ίο
    -0.07
     спіль
    -0.07
    conditionally
    -0.06
     года
    -0.06
     stocked
    -0.06
     Inputs
    -0.06
     Chairman
    -0.06
     textiles
    -0.06
    ฯ
    -0.06
     parole
    -0.06
    POSITIVE LOGITS
     は
    0.07
    yper
    0.07
    	screen
    0.07
    Deadline
    0.07
    */,
    0.06
    :],
    0.06
     ای
    0.06
    -----↵↵
    0.06
    ··
    0.06
     $?
    0.06
    Act Density 0.000%

    No Known Activations