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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     我
    -0.07
     прим
    -0.06
     Liz
    -0.06
     fır
    -0.06
     Explosion
    -0.06
    Ring
    -0.06
     �
    -0.06
    =C
    -0.06
    brid
    -0.06
    imetype
    -0.06
    POSITIVE LOGITS
    Yahoo
    0.07
    oq
    0.07
     Flutter
    0.07
     Von
    0.06
    -spacing
    0.06
    _tests
    0.06
    ......
    0.06
     Holder
    0.06
    づ
    0.06
     ask
    0.06
    Act Density 0.001%

    No Known Activations