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

    Neuronpedia

    INDEX
    Explanations

    tool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Swim
    -0.07
     Breath
    -0.06
     precisely
    -0.06
     denom
    -0.06
    /j
    -0.06
    [:,:
    -0.06
     feast
    -0.06
     Calvin
    -0.06
     Kings
    -0.06
     Modern
    -0.06
    POSITIVE LOGITS
    .",
↵
    0.07
     craw
    0.07
     обыч
    0.07
    barcode
    0.07
    TMP
    0.07
    リンク
    0.07
     зна
    0.07
     kep
    0.06
     جو
    0.06
    станов
    0.06
    Act Density 0.001%

    No Known Activations