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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    carrier
    -0.07
     fearful
    -0.07
     Be
    -0.06
     Oculus
    -0.06
     McCorm
    -0.06
     psycopg
    -0.06
     Hop
    -0.06
     Morm
    -0.06
    Descriptors
    -0.06
     oblig
    -0.06
    POSITIVE LOGITS
    驚
    0.08
    unte
    0.07
     čas
    0.06
    	rd
    0.06
     contacting
    0.06
    uters
    0.06
     chem
    0.06
    (channel
    0.06
    ende
    0.06
    traction
    0.06
    Act Density 0.170%

    No Known Activations