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

    Neuronpedia

    INDEX
    Explanations

    ads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Resist
    -0.07
     Occup
    -0.07
     Light
    -0.07
     Six
    -0.06
    验证
    -0.06
    י�
    -0.06
     iota
    -0.06
     Quit
    -0.06
     Peak
    -0.06
    Pooling
    -0.06
    POSITIVE LOGITS
     ads
    0.09
     brid
    0.06
    andır
    0.06
    踏
    0.06
    �다
    0.06
    -modal
    0.06
     uns
    0.06
     actresses
    0.06
     지역
    0.06
    :s
    0.06
    Act Density 0.002%

    No Known Activations