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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shuttle
    -0.07
     molt
    -0.07
     listened
    -0.06
     Spect
    -0.06
     carved
    -0.06
     spent
    -0.06
     Speedway
    -0.06
    games
    -0.06
    とも
    -0.06
    ']):
    -0.06
    POSITIVE LOGITS
    indows
    0.06
    aghetti
    0.06
    .'&
    0.06
    INUX
    0.06
    ishly
    0.06
    	die
    0.06
    alogy
    0.06
     kami
    0.06
    ิป
    0.06
     호텔
    0.06
    Act Density 0.044%

    No Known Activations