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

    Neuronpedia

    INDEX
    Explanations

    javascript testing framework jest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opes
    0.42
    auce
    0.41
    buildings
    0.40
    ence
    0.40
    ances
    0.40
    ility
    0.39
    ides
    0.39
    ilities
    0.38
    unce
    0.38
     heels
    0.38
    POSITIVE LOGITS
     circol
    0.43
     circ
    0.42
     quizá
    0.41
     circulating
    0.39
     sarkar
    0.39
    قم
    0.38
    詼
    0.37
     diatomic
    0.37
     talvez
    0.37
     transm
    0.36
    Act Density 0.001%

    No Known Activations