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

    Neuronpedia

    INDEX
    Explanations

    restitution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruku
    -0.07
    WhatsApp
    -0.07
     adulthood
    -0.07
    =msg
    -0.07
     افزار
    -0.06
    ĐT
    -0.06
     inaccurate
    -0.06
    功能
    -0.06
    اعب
    -0.06
    аду
    -0.06
    POSITIVE LOGITS
     restitution
    0.08
    opyright
    0.07
     remorse
    0.06
    oblins
    0.06
     Wohn
    0.06
    _GENER
    0.06
     patched
    0.06
    >Z
    0.06
    _complete
    0.06
    rx
    0.06
    Act Density 0.004%

    No Known Activations