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

    Neuronpedia

    INDEX
    Explanations

    member

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    以前
    -0.09
    raig
    -0.07
    大型
    -0.07
     Craig
    -0.07
    七月
    -0.07
    当时
    -0.07
     Us
    -0.07
    وب
    -0.07
    上游
    -0.07
     È
    -0.07
    POSITIVE LOGITS
    蔊
    0.07
     meddling
    0.07
    ccion
    0.06
    ꍲ
    0.06
     labeling
    0.06
     kutje
    0.06
    Ⲟ
    0.06
    ND
    0.06
    脬
    0.06
    �
    0.06
    Act Density 0.011%

    No Known Activations