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

    Neuronpedia

    INDEX
    Explanations

    graphics coordinate systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objectively
    -0.08
     Strategies
    -0.08
     psychologist
    -0.08
     Charles
    -0.08
    Strategies
    -0.08
     verdie
    -0.08
    Charles
    -0.08
     Colored
    -0.08
     misguided
    -0.07
     Strategy
    -0.07
    POSITIVE LOGITS
     wasi
    0.08
     Moro
    0.08
     Wasi
    0.08
     rechts
    0.08
    cto
    0.08
     fins
    0.07
     multiline
    0.07
     saranno
    0.07
     task
    0.07
     ā
    0.07
    Act Density 0.001%

    No Known Activations