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

    Neuronpedia

    INDEX
    Explanations

    general

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arcs
    -0.07
     بر
    -0.06
     استاد
    -0.06
    licted
    -0.06
     themed
    -0.06
    دار
    -0.06
     sibling
    -0.06
    ắt
    -0.06
     Clyde
    -0.06
     softer
    -0.06
    POSITIVE LOGITS
    _SPELL
    0.07
     smoke
    0.06
     hvis
    0.06
    ")){↵
    0.06
     Natural
    0.06
     glossy
    0.06
     Oscars
    0.06
     ventured
    0.06
     indx
    0.06
    0.06
    Act Density 0.002%

    No Known Activations