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

    Neuronpedia

    INDEX
    Explanations

    opening brackets

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    war
    -0.07
     sky
    -0.07
    Bal
    -0.07
    .DE
    -0.07
     leven
    -0.07
    @include
    -0.07
    也許
    -0.07
    虚
    -0.07
    火车站
    -0.06
     War
    -0.06
    POSITIVE LOGITS
    IDES
    0.07
    	Image
    0.07
    セフレ
    0.07
     egg
    0.07
    _HTML
    0.07
    Número
    0.07
    פש
    0.07
    ilers
    0.06
    곁
    0.06
     TCP
    0.06
    Act Density 0.129%

    No Known Activations