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

    Neuronpedia

    INDEX
    Explanations

    reek

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NSString
    -0.07
    ouched
    -0.07
     request
    -0.06
    兄
    -0.06
    ード
    -0.06
    	request
    -0.06
    믿
    -0.06
    usuarios
    -0.06
     Den
    -0.06
    ㎥
    -0.06
    POSITIVE LOGITS
     цель
    0.07
    它是
    0.07
    .parameters
    0.07
    لاقات
    0.07
    .alpha
    0.07
    _ability
    0.07
     Realt
    0.07
    实际上是
    0.07
    散文
    0.06
    هي
    0.06
    Act Density 0.001%

    No Known Activations