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

    Neuronpedia

    INDEX
    Explanations

    rewards and benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ஆடி
    0.85
    vout
    0.85
     tratt
    0.85
    ュ
    0.84
    जय
    0.81
    tanh
    0.81
    nast
    0.81
     cuid
    0.81
    gfx
    0.81
    unjung
    0.80
    POSITIVE LOGITS
     awarded
    1.12
     received
    1.07
    받
    1.04
     bestowed
    0.99
     granted
    0.99
     diberikan
    0.93
     Received
    0.91
     seekers
    0.91
     conferred
    0.91
     given
    0.87
    Act Density 0.741%

    No Known Activations