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

    Neuronpedia

    INDEX
    Explanations

    what works for someone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tb
    -0.07
    總統
    -0.07
     conhec
    -0.07
    .strokeStyle
    -0.07
      ↵↵↵
    -0.07
     BOX
    -0.07
    醭
    -0.07
     Blessed
    -0.07
    ()<<
    -0.07
    醵
    -0.07
    POSITIVE LOGITS
     arr
    0.07
    ingredients
    0.07
    =(
    0.07
    authorized
    0.07
    FTP
    0.07
    rees
    0.06
     comprar
    0.06
    .decrypt
    0.06
     omap
    0.06
    联络
    0.06
    Act Density 0.012%

    No Known Activations