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

    Neuronpedia

    INDEX
    Explanations

    server, next server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /"+
    0.50
    ന്റ്
    0.48
     frowning
    0.47
     sullen
    0.46
     halus
    0.45
     malleable
    0.45
    ^{-}\
    0.45
     shampoos
    0.44
     ಸಾಮಾನ್ಯ
    0.44
     pliable
    0.44
    POSITIVE LOGITS
    <0x80>
    0.42
     ø
    0.42
    highest
    0.40
    Speaker
    0.39
    цией
    0.39
    ecie
    0.39
    Publisher
    0.39
     UPD
    0.38
    re
    0.38
    deutsch
    0.38
    Act Density 0.000%

    No Known Activations