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

    Neuronpedia

    INDEX
    Explanations

    Arithmetic symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     невоз
    -0.07
    .SC
    -0.07
     bạc
    -0.07
    做得
    -0.06
    寇
    -0.06
    อนาค
    -0.06
     Paid
    -0.06
     hazard
    -0.06
     Islands
    -0.06
     run
    -0.06
    POSITIVE LOGITS
    olest
    0.08
    Tiny
    0.07
     stash
    0.07
    🕊
    0.07
    鞮
    0.06
     solder
    0.06
     beloved
    0.06
    ﮡ
    0.06
    �
    0.06
    _toolbar
    0.06
    Act Density 0.003%

    No Known Activations