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

    Neuronpedia

    INDEX
    Explanations

    looked down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mér
    0.52
     impossibility
    0.48
     Ấ
    0.47
    Mediterr
    0.45
    Ấ
    0.44
    MART
    0.44
    Applic
    0.44
    CapsLock
    0.43
    AnalyzeAction
    0.43
    جے
    0.43
    POSITIVE LOGITS
     Pember
    0.42
     получа
    0.42
     मनोर
    0.42
     keamanan
    0.42
     বজায়
    0.41
     bulund
    0.40
    ى
    0.40
     Фургал
    0.40
    tober
    0.40
    kenalkan
    0.40
    Act Density 0.002%

    No Known Activations