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

    Neuronpedia

    INDEX
    Explanations

    feedforward neural networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    1.53
    ekt
    1.22
     são
    1.22
    sourceforge
    1.22
     Hanya
    1.18
     sonho
    1.18
    신
    1.18
    senha
    1.17
    bau
    1.16
    mack
    1.16
    POSITIVE LOGITS
    i
    1.27
     critic
    1.27
    ہوری
    1.23
    ್ಣ
    1.20
    ";//
    1.20
     fender
    1.17
    क
    1.16
    瞋
    1.16
    CTION
    1.14
     adsorbent
    1.14
    Act Density 0.001%

    No Known Activations