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

    Neuronpedia

    INDEX
    Explanations

    cars and engines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    互动
    -0.10
     взаимодейств
    -0.09
     আত্ম
    -0.09
     interaction
    -0.08
     योगदान
    -0.08
     trách
    -0.08
    Interaction
    -0.08
     interpersonal
    -0.08
     mkdir
    -0.08
     आत्म
    -0.08
    POSITIVE LOGITS
    型号
    0.10
    规格
    0.10
     Ausstattung
    0.10
     оснащ
    0.09
     shipped
    0.09
     Qualcomm
    0.09
     specs
    0.09
    illed
    0.09
    售价
    0.09
    车型
    0.09
    Act Density 0.075%

    No Known Activations