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

    Neuronpedia

    INDEX
    Explanations

    words preceding conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enroll
    0.59
    /
    0.54
     enrolled
    0.53
    ómicos
    0.52
    И
    0.51
     Venezuela
    0.50
     enrol
    0.50
    ר
    0.50
     endure
    0.48
    on
    0.47
    POSITIVE LOGITS
    Neurons
    0.46
     Develop
    0.45
     funktion
    0.41
    മം
    0.40
     Staying
    0.40
     kult
    0.39
     README
    0.38
    aphylococcus
    0.38
    ഗ്രഹ
    0.38
    Ᏻ
    0.38
    Act Density 0.004%

    No Known Activations