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

    Neuronpedia

    INDEX
    Explanations

    consolidation, cord, control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ری
    0.55
    دا
    0.54
    רי
    0.49
    ث
    0.47
    ود
    0.47
    لی
    0.47
     nirvach
    0.47
    ۹
    0.46
    دی
    0.46
     demikian
    0.45
    POSITIVE LOGITS
    '
    0.70
    emark
    0.47
    ably
    0.47
    ekin
    0.46
     Holdings
    0.45
    amp
    0.44
     Mr
    0.43
    FIRST
    0.43
     connect
    0.42
    iker
    0.42
    Act Density 0.005%

    No Known Activations