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

    Neuronpedia

    INDEX
    Explanations

    Reasoning and argumentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Directive
    -0.07
     tutorials
    -0.06
     Geo
    -0.06
     oppressed
    -0.06
     SCC
    -0.06
     BG
    -0.06
    Shader
    -0.06
     Directory
    -0.06
    001
    -0.06
     BigNumber
    -0.05
    POSITIVE LOGITS
    /></
    0.07
     ред
    0.07
     Emacs
    0.07
     heading
    0.07
     impart
    0.07
     llev
    0.07
    	lcd
    0.06
    ireccion
    0.06
    .build
    0.06
    grim
    0.06
    Act Density 0.117%

    No Known Activations