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

    Neuronpedia

    INDEX
    Explanations

    km

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ind
    -0.08
    ตอน
    -0.07
     Saying
    -0.07
     unto
    -0.07
    “I
    -0.07
    seg
    -0.07
     props
    -0.07
    Metro
    -0.07
     ت
    -0.07
     ي
    -0.07
    POSITIVE LOGITS
     dejtingsaj
    0.07
    �
    0.07
    レーション
    0.07
    hk
    0.07
    �
    0.06
    门口
    0.06
    LOBAL
    0.06
     behaviour
    0.06
    ż
    0.06
    疗
    0.06
    Act Density 0.001%

    No Known Activations