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

    Neuronpedia

    INDEX
    Explanations

    rophic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inz
    -0.07
    [user
    -0.07
     cases
    -0.07
     SMS
    -0.06
     passes
    -0.06
    alah
    -0.06
     twins
    -0.06
     Case
    -0.06
     değildi
    -0.06
    _SHADOW
    -0.06
    POSITIVE LOGITS
     Insets
    0.08
    еч
    0.07
     长
    0.07
     Antib
    0.07
    ocz
    0.07
     익
    0.06
    doctype
    0.06
     防
    0.06
     Sở
    0.06
    	Integer
    0.06
    Act Density 0.001%

    No Known Activations