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

    Neuronpedia

    INDEX
    Explanations

    generic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restoration
    -0.07
     Disaster
    -0.06
    设置
    -0.06
     darker
    -0.06
     Albany
    -0.06
     بها
    -0.06
     decreased
    -0.06
     surgeons
    -0.06
     reboot
    -0.06
     installment
    -0.06
    POSITIVE LOGITS
     generic
    0.08
    .generic
    0.08
    _GENERIC
    0.08
    inf
    0.07
    -generic
    0.07
    .";
    0.07
    eresa
    0.07
     JPG
    0.07
     GE
    0.07
    __':↵
    0.07
    Act Density 0.003%

    No Known Activations