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
    \Unit
    -0.07
    (logits
    -0.07
    -users
    -0.07
     Поп
    -0.06
     مجلس
    -0.06
     GroupLayout
    -0.06
     Corp
    -0.06
    (person
    -0.06
    кта
    -0.06
     Gov
    -0.06
    POSITIVE LOGITS
     bh
    0.07
    �
    0.07
     Styled
    0.06
     ponto
    0.06
     weg
    0.06
    .Mouse
    0.06
    (Bundle
    0.06
    ellar
    0.06
     neste
    0.06
     آنچه
    0.06
    Act Density 0.000%

    No Known Activations