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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     количества
    -0.07
    eah
    -0.06
     allergic
    -0.06
     posters
    -0.06
     Sender
    -0.06
    chs
    -0.06
    .dequeue
    -0.06
    poster
    -0.06
     hostages
    -0.06
    IPv
    -0.06
    POSITIVE LOGITS
    سیون
    0.07
    ENCE
    0.07
    bones
    0.07
     uygulam
    0.06
     Stunden
    0.06
    Jane
    0.06
     faux
    0.06
     Datum
    0.06
    Thomas
    0.06
    การท
    0.06
    Act Density 0.000%

    No Known Activations