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

    Neuronpedia

    INDEX
    Explanations

    Sorry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pat
    -0.06
    ="/">
    -0.06
    僕
    -0.06
     renal
    -0.06
    $
↵
    -0.06
     Пос
    -0.05
     cụ
    -0.05
    BackStack
    -0.05
     credit
    -0.05
    Models
    -0.05
    POSITIVE LOGITS
     annonce
    0.07
    最后
    0.07
    modifiers
    0.07
     Desire
    0.06
     Scarlett
    0.06
    ycl
    0.06
    政策
    0.06
    noxious
    0.06
     candidacy
    0.06
    agma
    0.06
    Act Density 0.018%

    No Known Activations