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

    Neuronpedia

    INDEX
    Explanations

    API definitions, parameters, and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TensorFlow
    0.43
    <0x0D>
    0.39
    S
    0.39
    s
    0.38
    0.38
     (
    0.38
    t
    0.38
     XOR
    0.38
    ↵↵↵
    0.37
     이미
    0.37
    POSITIVE LOGITS
    <unused278>
    0.44
     vassals
    0.43
     liquors
    0.42
    <unused291>
    0.42
     electrified
    0.40
    ফুল্ল
    0.39
    <unused284>
    0.39
     handicrafts
    0.39
    <unused709>
    0.39
    <unused562>
    0.39
    Act Density 0.020%

    No Known Activations