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

    Neuronpedia

    INDEX
    Explanations

    connecting multiple ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਾਲ
    1.01
    Save
    0.97
    Titles
    0.96
    ્યા
    0.94
    "
    0.93
     Fatal
    0.93
    Inverse
    0.93
    Assign
    0.89
    Cum
    0.89
    ino
    0.88
    POSITIVE LOGITS
    以及
    1.53
     এবং
    1.49
     oraz
    1.40
     serta
    1.36
    及び
    1.33
     एवं
    1.26
     및
    1.25
     and
    1.24
     ஆகியவற்ற
    1.24
     consisting
    1.22
    Act Density 1.193%

    No Known Activations