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

    Neuronpedia

    INDEX
    Explanations

    million

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pageY
    -0.07
     dbs
    -0.07
     onData
    -0.07
    嘿嘿
    -0.07
     Gerr
    -0.07
     Vor
    -0.07
     gev
    -0.07
    说到这里
    -0.06
    真皮
    -0.06
     Lever
    -0.06
    POSITIVE LOGITS
    0.07
    otte
    0.07
    	flash
    0.07
     Şubat
    0.07
    iterate
    0.06
    айте
    0.06
    otten
    0.06
    -router
    0.06
     illustrated
    0.06
    _returns
    0.06
    Act Density 0.013%

    No Known Activations