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

    Neuronpedia

    INDEX
    Explanations

    displaying or ending code execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     어
    0.46
    can
    0.43
    keyPressed
    0.43
    eline
    0.43
    ور
    0.42
     trainers
    0.42
    0.42
    field
    0.41
    вая
    0.41
    ěž
    0.41
    POSITIVE LOGITS
     ذریعے
    0.45
    一款
    0.43
     indietro
    0.43
     udało
    0.42
     love
    0.42
     turmoil
    0.41
     ausschließlich
    0.40
     घेऊन
    0.39
     philosophies
    0.38
     fenomeno
    0.38
    Act Density 0.026%

    No Known Activations