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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ikko
    -0.08
    ’exploitation
    -0.08
    িয়া
    -0.07
    issus
    -0.07
     relentlessly
    -0.07
    оген
    -0.07
     ил
    -0.07
    żyt
    -0.07
     gloomy
    -0.07
    TXT
    -0.07
    POSITIVE LOGITS
     positiven
    0.09
     radians
    0.09
     ensured
    0.09
     positie
    0.09
     Hence
    0.09
     positive
    0.09
     (>
    0.08
    positive
    0.08
     position
    0.08
     hence
    0.08
    Act Density 0.041%

    No Known Activations