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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    intro
    -0.06
     Kotlin
    -0.06
    ену
    -0.06
    merge
    -0.06
    enge
    -0.06
     vengeance
    -0.06
    ENDOR
    -0.06
     Hansen
    -0.06
     frozen
    -0.06
    _mgr
    -0.06
    POSITIVE LOGITS
     impacted
    0.07
     seeming
    0.06
    (itemView
    0.06
    .Annotation
    0.06
     demographics
    0.06
     bzw
    0.06
    評
    0.06
     slogan
    0.06
    ↑
    0.06
    _dims
    0.06
    Act Density 0.052%

    No Known Activations