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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pragma
    -0.07
    (add
    -0.06
     सद
    -0.06
     средства
    -0.06
    .Te
    -0.06
    .dr
    -0.06
     compatible
    -0.06
    holm
    -0.06
    Z
    -0.06
    <'
    -0.06
    POSITIVE LOGITS
    �
    0.08
    artin
    0.07
     potom
    0.06
     พร
    0.06
     particular
    0.06
    .scrollHeight
    0.06
     kısm
    0.06
    landı
    0.06
     %>
    0.06
    !)
    0.06
    Act Density 0.000%

    No Known Activations