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

    Neuronpedia

    INDEX
    Explanations

    long duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -around
    -0.07
     Maurit
    -0.07
    DataService
    -0.07
    山县
    -0.07
    価
    -0.07
    渫
    -0.06
    协调
    -0.06
     Cush
    -0.06
     Rob
    -0.06
    (Const
    -0.06
    POSITIVE LOGITS
     deception
    0.08
    읻
    0.07
    .lists
    0.07
    诸葛亮
    0.07
    własn
    0.06
     athletics
    0.06
    𫸩
    0.06
     أيضا
    0.06
     households
    0.06
    _*
    0.06
    Act Density 0.042%

    No Known Activations