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

    Neuronpedia

    INDEX
    Explanations

    decision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sneakers
    -0.08
    प्त
    -0.08
    dating
    -0.08
    fees
    -0.08
    site
    -0.08
    aptured
    -0.07
    itr
    -0.07
    媽媽
    -0.07
     Motorrad
    -0.07
     gigant
    -0.07
    POSITIVE LOGITS
     actions
    0.10
     decisions
    0.10
     priorit
    0.09
     consciously
    0.09
     գործող
    0.09
    Align
    0.09
    行动
    0.09
     діяль
    0.08
     tindakan
    0.08
     shaping
    0.08
    Act Density 0.125%

    No Known Activations