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

    Neuronpedia

    INDEX
    Explanations

    meaningful, dear to heart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (target
    -0.07
     foto
    -0.06
     convin
    -0.06
    ｍ
    -0.06
    Harness
    -0.06
    리아
    -0.06
     defending
    -0.06
    	address
    -0.06
    shadow
    -0.06
    Option
    -0.06
    POSITIVE LOGITS
     xbmc
    0.07
    odě
    0.07
     Adidas
    0.07
     economists
    0.07
     looph
    0.06
    กำ
    0.06
    )sender
    0.06
    sched
    0.06
    _BAND
    0.06
    retry
    0.06
    Act Density 0.113%

    No Known Activations