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

    Neuronpedia

    INDEX
    Explanations

    AI integration, pruning, ulcers, API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಅಪಾಯ
    0.46
    問題を
    0.46
    gramModel
    0.45
     চলা
    0.45
    酢
    0.44
    บู
    0.42
     спект
    0.42
     renverse
    0.41
    மர்
    0.41
    OSITION
    0.41
    POSITIVE LOGITS
    omn
    0.53
    og
    0.52
     K
    0.49
     Aw
    0.48
    K
    0.48
     Universitas
    0.48
     D
    0.48
    otp
    0.47
    the
    0.46
    no
    0.46
    Act Density 0.001%

    No Known Activations