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

    Neuronpedia

    INDEX
    Explanations

    Technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
                            
↵
    -0.07
    ويل
    -0.07
    raison
    -0.06
     chuyển
    -0.06
     Kos
    -0.06
    .setItem
    -0.06
     Duc
    -0.06
     BaseActivity
    -0.06
    ...)↵
    -0.06
     CAP
    -0.06
    POSITIVE LOGITS
     (/
    0.07
    hind
    0.06
     datings
    0.06
     simplex
    0.06
     mlx
    0.06
     ObjectType
    0.06
     width
    0.06
    ƒ
    0.06
    QUIRES
    0.06
    conomy
    0.06
    Act Density 0.001%

    No Known Activations