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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cycle
    -0.07
     OTHERWISE
    -0.06
    腦
    -0.06
     usb
    -0.06
    Labels
    -0.06
     Zhao
    -0.06
    itos
    -0.06
     threads
    -0.06
     stages
    -0.06
    Injector
    -0.06
    POSITIVE LOGITS
     mandate
    0.07
    .Ma
    0.06
    нет
    0.06
     credited
    0.06
     tái
    0.06
     взгляд
    0.06
    _strlen
    0.06
    ENDOR
    0.06
    iasco
    0.06
    oblins
    0.06
    Act Density 0.051%

    No Known Activations