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

    Neuronpedia

    INDEX
    Explanations

    scanning, transcribe, custom, degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.49
    ’
    0.47
    য়
    0.44
     demise
    0.42
     grievances
    0.41
     dividends
    0.40
    י
    0.40
     tutur
    0.40
     emissions
    0.39
    '
    0.39
    POSITIVE LOGITS
    <unused25>
    0.48
    mér
    0.46
    觐
    0.45
    বার্ট
    0.45
     torneo
    0.44
     aktiviert
    0.44
    midt
    0.43
     कोड
    0.43
     Mujeres
    0.43
     Técn
    0.42
    Act Density 0.000%

    No Known Activations