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

    Neuronpedia

    INDEX
    Explanations

    if condition for catering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ร
    0.59
    Ş
    0.52
     etanol
    0.50
    प
    0.49
     së
    0.48
    งิน
    0.47
    Fuel
    0.47
    ย
    0.46
     dan
    0.46
    💨
    0.46
    POSITIVE LOGITS
     Trotsky
    0.45
     Confucian
    0.44
     Vietnamese
    0.44
     California
    0.42
     Jewish
    0.42
     Diffraction
    0.42
     Photoshop
    0.41
    يمان
    0.41
     Lower
    0.41
     Buddhist
    0.39
    Act Density 0.002%

    No Known Activations