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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tom
    -0.07
    鄱
    -0.06
     Le
    -0.06
    _SIZE
    -0.06
    筥
    -0.06
     reflective
    -0.06
     Tele
    -0.06
    :none
    -0.06
    빛
    -0.06
    🔽
    -0.06
    POSITIVE LOGITS
     Draco
    0.07
    bour
    0.07
     احد
    0.06
     necessity
    0.06
    הליכי
    0.06
    stitutions
    0.06
    	token
    0.06
    Classes
    0.06
    -ios
    0.06
    keyboard
    0.06
    Act Density 0.001%

    No Known Activations