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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Adapter
    -0.07
     autonomous
    -0.07
    .view
    -0.07
    ֆ
    -0.07
     chỉ
    -0.06
    �
    -0.06
     religious
    -0.06
     Chỉ
    -0.06
    ⽩
    -0.06
    iac
    -0.06
    POSITIVE LOGITS
    _meas
    0.08
    老化
    0.07
     CONT
    0.07
     elapsed
    0.07
     마지
    0.07
     disple
    0.07
    כת
    0.07
    恭敬
    0.07
    opa
    0.07
    挣钱
    0.07
    Act Density 0.057%

    No Known Activations