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

    Neuronpedia

    INDEX
    Explanations

    oxide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hunt
    -0.07
     diarr
    -0.07
    	HX
    -0.06
     combat
    -0.06
    new
    -0.06
    ło
    -0.06
     Nar
    -0.06
     berhasil
    -0.06
    ARR
    -0.06
    qrstuvwxyz
    -0.06
    POSITIVE LOGITS
    (profile
    0.07
    oxide
    0.07
    피
    0.07
    mere
    0.07
    	HANDLE
    0.07
    liable
    0.07
    .signIn
    0.07
     Rodney
    0.06
    %">
    0.06
    	code
    0.06
    Act Density 0.003%

    No Known Activations