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

    Neuronpedia

    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ROM
    -0.07
    dül
    -0.07
     UC
    -0.07
     gnome
    -0.06
     Chess
    -0.06
    DR
    -0.06
    _CHO
    -0.06
     aspect
    -0.06
     unintended
    -0.06
    FLOW
    -0.06
    POSITIVE LOGITS
    etections
    0.06
    cki
    0.06
    soap
    0.06
    连接
    0.06
    (delete
    0.06
     justified
    0.06
    excluding
    0.05
    CLUDING
    0.05
     Mor
    0.05
    yyval
    0.05
    Act Density 0.000%

    No Known Activations