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

    Neuronpedia

    INDEX
    Explanations

    model ** about model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nop
    0.46
     wur
    0.44
     deme
    0.44
     their
    0.44
     actions
    0.44
     pseudos
    0.43
     dah
    0.43
     margin
    0.43
     redacted
    0.42
     leurs
    0.41
    POSITIVE LOGITS
    蛩
    0.41
     κυ
    0.41
     йөк
    0.40
    しましょう
    0.40
    菽
    0.39
     எதிர்க
    0.38
    ুঁ
    0.38
     সাধারণত
    0.38
    运输
    0.38
     ሆ
    0.38
    Act Density 0.000%

    No Known Activations