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

    Neuronpedia

    INDEX
    Explanations

    usage documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     соединения
    0.40
    豚
    0.39
    થમ
    0.39
    Waiting
    0.38
     Waiting
    0.38
     Isol
    0.38
     учреждения
    0.37
     обез
    0.36
     mezcl
    0.35
    等待
    0.35
    POSITIVE LOGITS
     cynicism
    0.49
     wastage
    0.45
     rul
    0.44
     videos
    0.43
     phenylalanine
    0.41
     documentation
    0.39
    atitis
    0.39
    的网络
    0.39
     sing
    0.38
     doc
    0.38
    Act Density 0.000%

    No Known Activations