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

    Neuronpedia

    INDEX
    Explanations

    say ","

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     somebody
    -0.07
     thats
    -0.07
    .End
    -0.06
    -shop
    -0.06
     doctrine
    -0.06
     suc
    -0.06
    End
    -0.06
    _FLAGS
    -0.06
     Sap
    -0.06
     dumb
    -0.06
    POSITIVE LOGITS
     Sesso
    0.08
    INavigationController
    0.08
    'am
    0.07
    різ
    0.07
    солют
    0.07
     �
    0.06
    idge
    0.06
    ันว
    0.06
    ічна
    0.06
    ateur
    0.06
    Act Density 0.095%

    No Known Activations