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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .timezone
    -0.07
    .Extension
    -0.07
    Cs
    -0.07
     перевір
    -0.07
    _restore
    -0.07
     prisoners
    -0.07
     feats
    -0.07
    NotEmpty
    -0.07
     objs
    -0.06
     veterinary
    -0.06
    POSITIVE LOGITS
     Bender
    0.07
     ),
↵
    0.06
     다
    0.06
     Activ
    0.06
     you
    0.06
     만
    0.06
     ],
↵
    0.06
     Throughout
    0.06
     "");
↵
    0.06
     Broadcasting
    0.06
    Act Density 0.020%

    No Known Activations