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

    Neuronpedia

    INDEX
    Explanations

    Pageants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reproduc
    -0.09
     ioe
    -0.08
     forgotten
    -0.07
     mood
    -0.07
    ?action
    -0.07
    ***↵
    -0.07
     behe
    -0.07
    Dose
    -0.07
    _IO
    -0.07
     (**
    -0.07
    POSITIVE LOGITS
     конкурс
    0.10
     �
    0.09
     crowned
    0.09
     போட்ட
    0.09
     contestant
    0.09
     �
    0.08
     конкурса
    0.08
     நிற
    0.08
     मुक
    0.08
     विज
    0.08
    Act Density 0.007%

    No Known Activations