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

    Neuronpedia

    INDEX
    Explanations

    braces and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ']);
    0.52
     +=
    0.49
    p
    0.48
    ({
    0.48
    (
    0.46
    ","
    0.45
    x
    0.45
    ))
    0.45
     ({
    0.45
    .
    0.45
    POSITIVE LOGITS
     Oldborough
    0.54
     Põ
    0.49
     multifaceted
    0.48
     Arnhem
    0.48
     Abhäng
    0.46
     fudai
    0.45
     grafted
    0.45
    hil
    0.44
     नॉर्थ
    0.44
    ക്കൊ
    0.44
    Act Density 0.000%

    No Known Activations