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

    Neuronpedia

    INDEX
    Explanations

    programming technologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marathon
    -0.07
    EXPECTED
    -0.07
     useless
    -0.07
    䃎
    -0.07
    حلم
    -0.07
    alley
    -0.07
    蔊
    -0.07
    乐观
    -0.07
    �
    -0.07
    urved
    -0.07
    POSITIVE LOGITS
    ā
    0.07
    低头
    0.07
     WA
    0.07
    ō
    0.07
     Paw
    0.07
    _SORT
    0.07
    正
    0.06
     porch
    0.06
    quad
    0.06
    Positions
    0.06
    Act Density 0.171%

    No Known Activations