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

    Neuronpedia

    INDEX
    Explanations

    VMware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.73
    inį
    0.57
    ור
    0.57
    。
    0.57
    ToFile
    0.55
    лся
    0.54
    ۔
    0.54
    ou
    0.54
    inib
    0.54
    ssymb
    0.53
    POSITIVE LOGITS
    ’
    0.67
     इज़
    0.54
     रियलिटी
    0.54
    SER
    0.53
     स्टाइल
    0.53
    glycer
    0.49
    मॉन
    0.48
    hoppers
    0.48
    मे
    0.47
    MORE
    0.47
    Act Density 0.001%

    No Known Activations