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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pi
    0.49
     Herm
    0.47
    Validation
    0.46
    Herm
    0.46
    Im
    0.46
    扬
    0.45
     Marilyn
    0.43
    కి
    0.42
    רוי
    0.41
     Building
    0.40
    POSITIVE LOGITS
     trolls
    0.61
    ការពារ
    0.55
     diminishes
    0.55
     maliciously
    0.55
     anticipated
    0.54
     OUTER
    0.53
     sarkar
    0.53
     når
    0.52
     indistinct
    0.52
    easeInOut
    0.52
    Act Density 0.000%

    No Known Activations