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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    namely
    0.79
    �
    0.72
    train
    0.71
     syair
    0.68
    ?,?,
    0.66
    €™
    0.66
    !');
    0.65
    mathrm
    0.65
    {}'.
    0.64
    !',
    0.64
    POSITIVE LOGITS
     This
    1.40
     Although
    1.28
     You
    1.25
     They
    1.22
     There
    1.22
     These
    1.21
     Even
    1.19
     Provides
    1.19
     Many
    1.16
     We
    1.15
    Act Density 0.832%

    No Known Activations