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

    Neuronpedia

    INDEX
    Explanations

    planets and moons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _median
    -0.07
    grams
    -0.07
    (Input
    -0.07
    пат
    -0.06
    iore
    -0.06
     عبد
    -0.06
     Boston
    -0.06
    -no
    -0.06
    .bottom
    -0.06
     Temperature
    -0.06
    POSITIVE LOGITS
     Rough
    0.06
     Context
    0.06
    
    0.06
    \L
    0.06
     leveraging
    0.06
     profiler
    0.06
    -progress
    0.06
    (steps
    0.06
     Sylv
    0.06
    .son
    0.06
    Act Density 0.041%

    No Known Activations