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

    Neuronpedia

    INDEX
    Explanations

    when considering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     자주
    0.46
    Ḩ
    0.45
     WebDriver
    0.45
    khidmat
    0.44
     frequency
    0.44
    Frequency
    0.44
    频率
    0.43
     आवृत्ति
    0.42
     transmittance
    0.42
    Agregar
    0.42
    POSITIVE LOGITS
     consider
    0.51
     consid
    0.46
     considér
    0.45
     considera
    0.45
     consideran
    0.45
     плани
    0.42
     considering
    0.42
     considere
    0.40
     considered
    0.40
     considère
    0.39
    Act Density 0.000%

    No Known Activations