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

    Neuronpedia

    INDEX
    Explanations

    generating and distributing illegal keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coln
    1.10
     inter
    1.02
    inter
    0.97
    S
    0.95
    <div>
    0.94
    턴
    0.94
    TTS
    0.93
    volume
    0.91
     χω
    0.90
    SVC
    0.90
    POSITIVE LOGITS
    theorem
    1.45
    keits
    1.33
    erche
    1.30
    ع
    1.27
    علم
    1.25
    diamonds
    1.22
    Ď
    1.22
     accad
    1.21
    عرض
    1.21
     tarses
    1.20
    Act Density 0.001%

    No Known Activations