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

    Neuronpedia

    INDEX
    Explanations

    HTML/formatting/grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    últ
    -0.08
     golfing
    -0.08
    permission
    -0.08
    IQ
    -0.07
    Tools
    -0.07
     本
    -0.07
    tools
    -0.07
     Buddhist
    -0.07
    साय
    -0.07
    Normal
    -0.07
    POSITIVE LOGITS
     roses
    0.09
     ausges
    0.08
     Castle
    0.08
     Ier
    0.07
     Roses
    0.07
    Castle
    0.07
    oon
    0.07
     nat
    0.07
    ρού
    0.07
     tailoring
    0.07
    Act Density 0.005%

    No Known Activations