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

    Neuronpedia

    INDEX
    Explanations

    broken mirror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ट
    1.75
    推广
    1.59
    স্থা
    1.50
     اجلاس
    1.46
    ^(
    1.44
     sponsorship
    1.43
    शहर
    1.43
    bü
    1.43
    ದೇಶ
    1.40
    şen
    1.40
    POSITIVE LOGITS
    srv
    1.62
    скоп
    1.44
    IENTS
    1.39
    oze
    1.38
    swift
    1.35
    iop
    1.34
    patients
    1.32
    translated
    1.29
    accessible
    1.28
    όν
    1.27
    Act Density 0.008%

    No Known Activations