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

    Neuronpedia

    INDEX
    Explanations

    restraint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="<
    -0.07
    だって
    -0.07
     upd
    -0.07
     مدير
    -0.07
    Mini
    -0.07
    )i
    -0.07
    ัตว
    -0.07
     Ended
    -0.07
    知道
    -0.06
    eddar
    -0.06
    POSITIVE LOGITS
    ö
    0.06
     Intro
    0.06
     Nicholas
    0.06
    ίνει
    0.06
    _INCREF
    0.06
     Warwick
    0.06
    Vu
    0.06
    REQUEST
    0.06
    _SWAP
    0.06
    ¼
    0.05
    Act Density 0.013%

    No Known Activations