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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hardest
    -0.07
    (par
    -0.06
     Myth
    -0.06
     Ser
    -0.06
    ляются
    -0.06
    	add
    -0.06
    撤
    -0.06
     LTE
    -0.06
    ISS
    -0.06
     strengths
    -0.06
    POSITIVE LOGITS
    OPTIONS
    0.07
    yi
    0.06
     Rolex
    0.06
     높은
    0.06
    jsx
    0.06
    Cent
    0.06
    alborg
    0.06
    -flag
    0.06
     UIBarButtonItem
    0.06
    rieving
    0.06
    Act Density 0.025%

    No Known Activations