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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Delhi
    -0.07
    Grand
    -0.06
     folklore
    -0.06
     Seminar
    -0.06
     Vaugh
    -0.06
     UsersController
    -0.06
    .NoArgsConstructor
    -0.06
     pohled
    -0.06
     pnl
    -0.06
    "]=$
    -0.06
    POSITIVE LOGITS
    svc
    0.07
    712
    0.07
    фров
    0.07
     hookup
    0.07
    лина
    0.07
    afe
    0.07
    (object
    0.07
     примен
    0.07
     Blogger
    0.06
     backbone
    0.06
    Act Density 0.009%

    No Known Activations