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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     killed
    -0.06
    80
    -0.06
    %n
    -0.06
     initial
    -0.06
     denom
    -0.06
     Ung
    -0.06
     offsetX
    -0.05
     PNG
    -0.05
     Gow
    -0.05
     undead
    -0.05
    POSITIVE LOGITS
     self
    0.08
    	self
    0.07
    -The
    0.07
    -the
    0.07
    =self
    0.07
    (self
    0.07
    我们
    0.07
     The
    0.07
    this
    0.07
    builtin
    0.07
    Act Density 0.044%

    No Known Activations