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

    Neuronpedia

    INDEX
    Explanations

    which corresponds, Flying Business, module greeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amenities
    0.47
     shared
    0.46
    Shared
    0.45
    shared
    0.43
     सुविधाएं
    0.43
    Ing
    0.43
    ARO
    0.41
     Shared
    0.40
    autions
    0.40
    olov
    0.40
    POSITIVE LOGITS
    wikkel
    0.41
     immort
    0.38
    硏
    0.38
     conoscere
    0.37
    👱
    0.37
    WithDictionary
    0.37
     near
    0.36
    🔩
    0.36
     centena
    0.36
     combinatorial
    0.36
    Act Density 0.000%

    No Known Activations