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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    έρα
    -0.08
    iras
    -0.08
    -0.07
    카라
    -0.07
    -0.07
    ENDIF
    -0.07
    τός
    -0.07
    -0.06
     seguint
    -0.06
    	NdrFcShort
    -0.06
    POSITIVE LOGITS
     spun
    0.07
     Them
    0.07
    -pre
    0.06
     Touch
    0.06
     equals
    0.06
     damned
    0.06
     Sty
    0.06
    	channel
    0.06
     muscles
    0.06
     touch
    0.06
    Act Density 0.007%

    No Known Activations