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

    Neuronpedia

    INDEX
    Explanations

    Lists and arithmetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /context
    -0.08
    /-
    -0.08
     ending
    -0.08
    	endif
    -0.07
     purposes
    -0.07
    enda
    -0.07
     manipul
    -0.07
     manipulation
    -0.07
     attaching
    -0.07
    ensch
    -0.07
    POSITIVE LOGITS
     tomo
    0.08
     importantly
    0.08
     stint
    0.08
     sept
    0.07
     tslint
    0.07
     cljs
    0.07
     vele
    0.07
     gulf
    0.07
    fragt
    0.07
     Platform
    0.07
    Act Density 0.061%

    No Known Activations