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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disappears
    -0.07
    -begin
    -0.07
     byl
    -0.07
     Markus
    -0.06
     qt
    -0.06
    Backup
    -0.06
    -wrap
    -0.06
     byla
    -0.06
    .standard
    -0.06
     noticed
    -0.06
    POSITIVE LOGITS
     تعریف
    0.08
     بالن
    0.07
     والن
    0.07
     nature
    0.07
     друго
    0.07
     Với
    0.06
    ��
    0.06
     Ül
    0.06
    erville
    0.06
     αυ
    0.06
    Act Density 0.068%

    No Known Activations