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

    Neuronpedia

    INDEX
    Explanations

    preposition followed by "a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    จาก
    0.64
     with
    0.63
     from
    0.61
     to
    0.61
     vorhand
    0.60
     των
    0.60
     when
    0.58
    Any
    0.57
     provenienti
    0.57
     you
    0.57
    POSITIVE LOGITS
     hilarious
    0.87
     fascinating
    0.85
     strikingly
    0.77
     intriguing
    0.77
     unmistakable
    0.77
     remarkable
    0.76
     incredible
    0.75
     admirable
    0.73
     undeniably
    0.73
     magnificent
    0.72
    Act Density 0.294%

    No Known Activations