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

    Neuronpedia

    INDEX
    Explanations

    001

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trilogy
    -0.08
     spanking
    -0.07
    _J
    -0.07
    mvc
    -0.07
    má
    -0.07
    _F
    -0.07
    	String
    -0.07
     foll
    -0.06
    	gl
    -0.06
    toi
    -0.06
    POSITIVE LOGITS
    CONFIG
    0.07
    controlled
    0.07
     bộ
    0.06
    lename
    0.06
     Ou
    0.06
    ichtet
    0.06
    addon
    0.06
    oracle
    0.06
     crews
    0.06
     sapi
    0.06
    Act Density 0.001%

    No Known Activations