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

    Neuronpedia

    INDEX
    Explanations

    rent, shuttle, car, taxis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Samples
    0.39
    思维
    0.39
    Sample
    0.38
    囿
    0.36
    Of
    0.36
    Nota
    0.36
     За
    0.36
     UP
    0.36
     kap
    0.35
    向上
    0.35
    POSITIVE LOGITS
     joe
    0.37
     lute
    0.37
    htub
    0.36
     initialized
    0.36
     হাসান
    0.35
    supporters
    0.35
    elje
    0.35
     lhs
    0.35
     اهم
    0.35
     તેવી
    0.35
    Act Density 0.000%

    No Known Activations